Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

The study included four separate surveys:

1. The LSMS survey of general population of Serbia in 2002

2. The survey of Family Income Support (MOP in Serbian) recipients in 2002 These two datasets are published together separately from the 2003 datasets.

3. The LSMS survey of general population of Serbia in 2003 (panel survey)

4. The survey of Roma from Roma settlements in 2003 These two datasets are published together.

Objectives

LSMS represents multi-topical study of household living standard and is based on international experience in designing and conducting this type of research. The basic survey was carried out in 2002 on a representative sample of households in Serbia (without Kosovo and Metohija). Its goal was to establish a poverty profile according to the comprehensive data on welfare of households and to identify vulnerable groups. Also its aim was to assess the targeting of safety net programs by collecting detailed information from individuals on participation in specific government social programs. This study was used as the basic document in developing Poverty Reduction Strategy (PRS) in Serbia which was adopted by the Government of the Republic of Serbia in October 2003.

The survey was repeated in 2003 on a panel sample (the households which participated in 2002 survey were re-interviewed).

Analysis of the take-up and profile of the population in 2003 was the first step towards formulating the system of monitoring in the Poverty Reduction Strategy (PRS). The survey was conducted in accordance with the same methodological principles used in 2002 survey, with necessary changes referring only to the content of certain modules and the reduction in sample size. The aim of the repeated survey was to obtain panel data to enable monitoring of the change in the living standard within a period of one year, thus indicating whether there had been a decrease or increase in poverty in Serbia in the course of 2003. [Note: Panel data are the data obtained on the sample of households which participated in the both surveys. These data made possible tracking of living standard of the same persons in the period of one year.]

Along with these two comprehensive surveys, conducted on national and regional representative samples which were to give a picture of the general population, there were also two surveys with particular emphasis on vulnerable groups. In 2002, it was the survey of living standard of Family Income Support recipients with an aim to validate this state supported program of social welfare. In 2003 the survey of Roma from Roma settlements was conducted. Since all present experiences indicated that this was one of the most vulnerable groups on the territory of Serbia and Montenegro, but with no ample research of poverty of Roma population made, the aim of the survey was to compare poverty of this group with poverty of basic population and to establish which categories of Roma population were at the greatest risk of poverty in 2003. However, it is necessary to stress that the LSMS of the Roma population comprised potentially most imperilled Roma, while the Roma integrated in the main population were not included in this study.

Geographic coverage

The surveys were conducted on the whole territory of Serbia (without Kosovo and Metohija).

Kind of data

Sample survey data [ssd]

Sampling procedure

Sample frame for both surveys of general population (LSMS) in 2002 and 2003 consisted of all permanent residents of Serbia, without the population of Kosovo and Metohija, according to definition of permanently resident population contained in UN Recommendations for Population Censuses, which were applied in 2002 Census of Population in the Republic of Serbia. Therefore, permanent residents were all persons living in the territory Serbia longer than one year, with the exception of diplomatic and consular staff.

The sample frame for the survey of Family Income Support recipients included all current recipients of this program on the territory of Serbia based on the official list of recipients given by Ministry of Social affairs.

The definition of the Roma population from Roma settlements was faced with obstacles since precise data on the total number of Roma population in Serbia are not available. According to the last population Census from 2002 there were 108,000 Roma citizens, but the data from the Census are thought to significantly underestimate the total number of the Roma population. However, since no other more precise data were available, this number was taken as the basis for estimate on Roma population from Roma settlements. According to the 2002 Census, settlements with at least 7% of the total population who declared itself as belonging to Roma nationality were selected. A total of 83% or 90,000 self-declared Roma lived in the settlements that were defined in this way and this number was taken as the sample frame for Roma from Roma settlements.

Planned sample: In 2002 the planned size of the sample of general population included 6.500 households. The sample was both nationally and regionally representative (representative on each individual stratum). In 2003 the planned panel sample size was 3.000 households. In order to preserve the representative quality of the sample, we kept every other census block unit of the large sample realized in 2002. This way we kept the identical allocation by strata. In selected census block unit, the same households were interviewed as in the basic survey in 2002. The planned sample of Family Income Support recipients in 2002 and Roma from Roma settlements in 2003 was 500 households for each group.

Sample type: In both national surveys the implemented sample was a two-stage stratified sample. Units of the first stage were enumeration districts, and units of the second stage were the households. In the basic 2002 survey, enumeration districts were selected with probability proportional to number of households, so that the enumeration districts with bigger number of households have a higher probability of selection. In the repeated survey in 2003, first-stage units (census block units) were selected from the basic sample obtained in 2002 by including only even numbered census block units. In practice this meant that every second census block unit from the previous survey was included in the sample. In each selected enumeration district the same households interviewed in the previous round were included and interviewed. On finishing the survey in 2003 the cases were merged both on the level of households and members.

Stratification: Municipalities are stratified into the following six territorial strata: Vojvodina, Belgrade, Western Serbia, Central Serbia (Šumadija and Pomoravlje), Eastern Serbia and South-east Serbia. Primary units of selection are further stratified into enumeration districts which belong to urban type of settlements and enumeration districts which belong to rural type of settlement.

The sample of Family Income Support recipients represented the cases chosen randomly from the official list of recipients provided by Ministry of Social Affairs. The sample of Roma from Roma settlements was, as in the national survey, a two-staged stratified sample, but the units in the first stage were settlements where Roma population was represented in the percentage over 7%, and the units of the second stage were Roma households. Settlements are stratified in three territorial strata: Vojvodina, Beograd and Central Serbia.

Mode of data collection

Face-to-face [f2f]

Research instrument

In all surveys the same questionnaire with minimal changes was used. It included different modules, topically separate areas which had an aim of perceiving the living standard of households from different angles. Topic areas were the following: 1. Roster with demography. 2. Housing conditions and durables module with information on the age of durables owned by a household with a special block focused on collecting information on energy billing, payments, and usage. 3. Diary of food expenditures (weekly), including home production, gifts and transfers in kind. 4. Questionnaire of main expenditure-based recall periods sufficient to enable construction of annual consumption at the household level, including home production, gifts and transfers in kind. 5. Agricultural production for all households which cultivate 10+ acres of land or who breed cattle. 6. Participation and social transfers module with detailed breakdown by programs 7. Labour Market module in line with a simplified version of the Labour Force Survey (LFS), with special additional questions to capture various informal sector activities, and providing information on earnings 8. Health with a focus on utilization of services and expenditures (including informal payments) 9. Education module, which incorporated pre-school, compulsory primary education, secondary education and university education. 10. Special income block, focusing on sources of income not covered in other parts (with a focus on remittances).

Response rate

During field work, interviewers kept a precise diary of interviews, recording both successful and unsuccessful visits. Particular attention was paid to reasons why some households were not interviewed. Separate marks were given for households which were not interviewed due to refusal and for cases when a given household could not be found on the territory of the chosen census block.

In 2002 a total of 7,491 households were contacted. Of this number a total of 6,386 households in 621 census rounds were interviewed. Interviewers did not manage to collect the data for 1,106 or 14.8% of selected households. Out of this number 634 households

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

The survey on financial literacy among the citizens of Bosnia and Herzegovina was conducted within a larger project that aims at creating the Action Plan for Consumer Protection in Financial Services.

The conclusion about the need for an Action Plan was reached by the representatives of the World Bank, the Federal Ministry of Finance, the Central Bank of Bosnia and Herzegovina, supervisory authorities for entity financial institutions and non-governmental organizations for the protection of consumer rights, based on the Diagnostic Review on Consumer Protection and Financial Literacy in Bosnia and Herzegovina conducted by the World Bank in 2009-2010. This diagnostic review was conducted at the request of the Federal Ministry of Finance, as part of a larger World Bank pilot program to assess consumer protection and financial literacy in developing countries and middle-income countries. The diagnostic review in Bosnia and Herzegovina was the eighth within this project.

The financial literacy survey, whose results are presented in this report, aims at establishing the basic situation with respect to financial literacy, serving on the one hand as a preparation for the educational activities plan, and on the other as a basis for measuring the efficiency of activities undertaken.

Geographic coverage

Data collection was based on a random, nation-wide sample of citizens of Bosnia and Herzegovina aged 18 or older (N = 1036).

Analysis unit

Household, individual

Universe

Population aged 18 or older

Kind of data

Sample survey data [ssd]

Sampling procedure

SUMMARY

In Bosnia and Herzegovina, as is well known, there is no completely reliable sample frame or information about universe. The main reasons for such a situation are migrations caused by war and lack of recent census data. The last census dates back to 1991, but since then the size and distribution of population has significantly changed. In such a situation, researchers have to combine all available sources of population data to estimate the present size and structure of the population: estimates by official statistical offices and international organizations, voters? lists, list of polling stations, registries of passport and ID holders, data from large random surveys etc.

The sample was three-stage stratified: in the first stage by entity, in the second by county/region and in the third by type of settlement (urban/rural). This means that, in the first stage, the total sample size was divided in two parts proportionally to number of inhabitants by entity, while in the second stage the subsample size for each entity was further divided by regions/counties. In the third stage, the subsample for each region/county was divided in two categories according to settlement type (rural/urban).

Taking into the account the lack of a reliable and complete list of citizens to be used as a sample frame, a multistage sampling method was applied. The list of polling stations was used as a frame for the selection of primary sampling units (PSU). Polling station territories are a good choice for such a procedure since they have been recently updated, for the general elections held in October 2010. The list of polling station territories contains a list of addresses of housing units that are certainly occupied.

In the second stage, households were used as a secondary sampling unit. Households were selected randomly by a random route technique. In total, 104 PSU were selected with an average of 10 respondents per PSU. The respondent from the selected household was selected randomly using the Trohdal-Bryant scheme.

In total, 1036 citizens were interviewed with a satisfactory response rate of around 60% (table 1). A higher refusal rate is recorded among middle-age groups (table 2). The theoretical margin of error for a random sample of this size is +/-3.0%.

Due to refusals, the sample structure deviated from the estimated population structure by gender, age and education level. Deviations were corrected by RIM weighting procedure.

MORE DETAILED INFORMATION

IPSOS designed a representative sample of approximately 1.000 residents age 18 and over, proportional to the adult populations of each region, based on age, sex, region and town (settlement) type.

For this research we designed three-stage stratified representative sample. First we stratify sample at entity level, regional level and then at settlement type level for each region.

Sample universe:

Population of B&H -18+; 1991 Census figures and estimated population dynamics, census figures of refugees and IDPs, 1996. Central Election Commision - 2008; CIPS - 2008;

Sampling frame:

Polling stations territory (approximate size of census units) within strata defined by regions and type of settlements (urban and rural) Polling stations territories are chosen to be used as primary units because it enables the most reliable sample selection, due to the fact that for these units the most complete data are available (dwelling register - addresses)

Type of sample:

Three stage random representative stratified sample

Definition and number of PSU, SSU, TSU, and sampling points

• PSU - Polling station territory Definition: Polling stations territories are defined by street(s) name(s) and dwelling numbers; each polling station territory comprises approximately 300 households, with exception of the settlements with less than 300 HH which are defined as one unite. Number of PSUs in sample universe: 4710
• SSU - Household Definition: One household comprises people living in the same apartment and sharing the expenditure for food
• TSU - Respondent Definition: Member of the HH , 18+ Number of TSUs in sample universe: = 2.966.766
• Sampling points Approximately 10 respondents per one PSU, total 104

Stratification, purpose and method

• First level strata: Federation of B&H Republika Srpska Brc ko District
• Second level strata: 10 cantons 2 regions -
• Third level strata: urban and rural settlements
• Purpose: Optimisation of the sample plan, and reducing the sampling error

• Method: The strata are defined by criteria of optimal geographical and cultural uniformity

• Selection procedure of PSU, SSU, and respondent Stratification, purpose and method

• PSU Type of sampling of the PSU: Polling station territory chosen with probability proportional to size (PPS) Method of selection: Cumulative (Lachirie method)

• SSU Type of sampling of the SSU: Sample random sampling without replacement Method of selection: Random walk - Random choice of the starting point

• TSU - Respondent Type of sampling of respondent: Sample random sampling without replacement Method of selection: TCB (Trohdal-Bryant scheme)

• Sample size N=1036 respondents

• Sampling error Marginal error +/-3.0%

Mode of data collection

Face-to-face [f2f]

Research instrument

The survey was modelled after the identical survey conducted in Romania. The questionnaire used in the Financial Literacy Survey in Romania was localized for Bosnia and Herzegovina, including adaptations to match the Bosnian context and methodological improvements in wording of questions.

Cleaning operations

Before data entry, 100% logic and consistency controls are performed first by local supervisors and once later by staff in central office.

Verification of correct data entry is assured by using BLAISE system for data entry (commercial product of Netherlands statistics), where criteria for logical and consistency control are defined in advance.

Response rate

• Nobody at home: 2,8%
• Eligible person is not home: 2,8%
• Refusal : 32,79%
• Given up after a minimum of two visits: 0,82%
• Other (excluded after control): 0,29%
• Finished: 60,5%

Abstract

The Tanzania Demographic and Health Survey (TDHS) is a national sample survey of women of reproductive ages (15-49) and men aged 15 to 60. The survey was designed to collect data on socioeconomic characteristics, marriage patterns, birth history, breastfeeding, use of contraception, immunisation of children, accessibility to health and family planning services, treatment of children during times of illness, and the nutritional status of children and their mothers.

The primary objectives of the TDHS were to: - Collect data for the evaluation of family planning and health programmes, - Determine the contraceptive prevalence rate, which will help in the design of future national family planning programmes, and - Assess the demographic situation of the country.

Geographic coverage

The Tanzania Demographic and Health Survey (TDHS) is a national sample survey. This sample should allow for separate analyses in urban and rural areas, and for estimation of contraceptive use in each of the 20 regions located on the mainland and in Zanzibar.

Analysis unit

• Households
• Children under five years
• Women age 15-49
• Men age 15-60

Kind of data

Sample survey data

Sampling procedure

The principal objective of the Tanzania Demographic and Health Survey (TDHS) was to collect data on fertility, family planning, and health of the people. This survey involved randomly selected women aged 15-49 and men aged 15-60 in selected households.

Before the sampling frame was developed, two possibilities for the TDHS sample design were considered: - The 1988 Population census list of Enumeration Areas (EAs) - The National Master Sample for Tanzania created in 1986 (NMS).

The NMS was intended mainly for agricultural purposes and, at that time, only for rural areas. The NMS was based on the 1978 Census information while the urban frame was still being worked upon. Therefore, it was decided that the TDHS sample design would use the 1988 Census information as the basic sampling frame. Since the TDHS sample was to be clustered, it was necessary to have sampling units of manageable and fairly uniform size and with very well defined boundaries. The 1988 Census frame provided the list of enumeration area units (EAs) that had well defined boundaries and manageable uniform size. Therefore, EAs were used as primary sampling units (PSUs).

The target of the TDHS sample was about 7850 women age 15-49 with completed interviews. This sample should allow for separate analyses in urban and rural areas, and for estimation of contraceptive use in each of the 20 regions located on the mainland and in Zanzibar. Estimates for large domains (by combination of a group of regions) were also taken into consideration.

The TDHS used a three-stage sample. The frame was stratified by urban and rural areas. The primary sampling units in the TDHS survey were the wards/branches. The design involved the target of 350 completed interviews for each of 19 regions on the mainland and 500 in each of Dar es Salaam and Zanzibar.

In the first stage, the wards/branches were systematically selected with probability proportional to size (according to 1988 census information). In a second sampling stage, two EAs per selected rural ward/branch and one EA per selected urban ward/branch were chosen with probability proportional to size (also according to 1988 census information). In total, 357 EAs were selected for the TDHS, 95 in the urban area and 262 in the rural. A new listing of households was made shortly before the TDHS fieldwork by special teams including a total of 14 field workers. These teams visited the selected EAs all over the country to list the names of the heads of the households and obtain the population composition of each household (total number of persons in the household). In urban areas, the address of the dwelling was also recorded in order to make it easy to identify the household during the main survey. A fixed number of 30 households in each rural EA and 20 in each urban EA were selected.

About 9560 households were needed to achieve the required sample size, assuming 80 percent overall household completion rate.

See detailed sampling information in the APPENDIX B of the final 1991-1992 Tanzania Demographic and Health Survey report.

Mode of data collection

Face-to-face

Research instrument

The household, female, and male questionnaires were designed by following the Model Questionnaire "B" which is for low contraceptive prevalence countries. Some adaptations were made to suit the Tanzania situation, but the core questions were not changed. The original questionnaire was prepared in English and later translated into Kiswahili, the language that is widely spoken in the country. There are parts in the country where people are not very conversant with Kiswahili and would find it difficult to respond in Kiswahili but would understand when they are asked anything. The translated document was given to another translator to translate it back into English and comparisons were made to determine the differences.

PRETEST

A pretest to assess the viability of the survey instruments, particularly the questionnaires and the field organization, was carried out in Iringa Rural District, Iringa Region. It covered 16 enumeration areas with a total of 320 households. The pretest, which took a month to complete, was carded out in November/December, 1990, and covered both rural and urban EAs.

The pretest training took two weeks and consisted of classroom training and field practice in neighborhood areas. In all, 14 newly recruited interviewers and the Census staff were involved. The Census staffs who were to be transformed into the TDHS team handled the training for both the fieldwork management and the questionnaire. During the later fieldwork, they supervised the field exercise.

During the fieldwork, the administrative structure of the CCM Party, which involved the Party Branch Offices and the ten-cell leadership, were utilized in an effort to secure the maximum confidence and cooperation of the people in the areas where the team was working. At the end of the fieldwork, the interviewers and the supervisory team returned to the head office in Dares Salaam for debriefing and discussion of their field experiences, particularly those related to the questionnaires and the logistic problems that were encountered. All these experiences were used to improve upon the final version of the questionnaires and the overall logistic arrangements.

Response rate

Out of the 9282 households selected for interview, 8561 households could be located and 8327 were actually interviewed. The shortfall between selected and interviewed households was largely due to the fact that many dwellings were either vacant or destroyed or no competent respondents were present at the time of the interview. A total of 9647 eligible women (i.e., women age 15-49 who spent the night before the interview in a sampled household) were identified for interview, and 9238 women were actually interviewed (96 percent response rate). The main reason for non-interview was absence from the home or incapacitation.

The Tanzania DHS male survey covered men aged between 15 and 60 years who were living in selected households (every fourth household of the female survey). The results of the survey show that 2392 eligible men were identified and 2114 men were interviewed (88 percent response rate). Men were generally not interviewed because they were either incapacitated or not at home during the time of the survey.

Sampling error estimates

The results from sample surveys are affected by two types of errors, non-sampling error and sampling error. Non-sampling error is due to mistakes made in carrying out field activities, such as failure to locate and interview the correct household, errors in the way the questions are asked, misunderstanding on the part of either the interviewer or the respondent, and data entry errors. Although efforts were made to minimize this type of error during the design and implementation of the TDHS, non-sampling errors are impossible to avoid and difficult to evaluate statistically.

Sampling errors, on the other hand, can be measured statistically. The sample of women selected in the TDHS is only one of many samples that could have been selected from the same population, using the same design and expected size. Each one would have yielded results that differed somewhat from the actual sample selected. The sampling error is a measure of the variability between all possible samples; although it is not known exactly, it can be estimated from the survey results.

Sampling error is usually measured in terms of standard error of a particular statistic (mean, percentage, etc.), which is the square root of the variance. The standard error can be used to calculate confidence intervals within which one can be reasonably assured that, apart from non-sampling errors, the true value of the variable for the whole population falls. For example, for any given statistic calculated from a sample survey, the value of that same statistic as measured in 95 percent of all possible samples with the same design (and expected size) will fall within a range of plus or minus two times the standard error of that statistic.

If the sample of women had been selected as a simple random sample, it would have been possible to use straightforward formulas for calculating sampling errors. However, the Tanzania DHS sample designs depended on stratification, stages, and clusters. Consequently, it was necessary to utilize more complex formulas. The computer package CLUSTERS, developed by the International Statistical

Abstract

The objective of the endline surveys in 2016 were to gather household, biomedical, and cognition data in order to evaluate the long-term impact of home supplementation with micronutrient powders (MNP), when combined with seasonal malaria chemoprevention (SMC) and early stimulation, delivered through community preschools and parenting sessions, on the health and cognitive development of children during the first five years of life.

The trial consisted of 3 arms. First, 60 villages with established Early Childhood Development centres (ECD) were randomised to 1 of 2 arms:

1) Children living in villages in the ECD control arm received SMC as part of national health programming and a national parenting intervention delivered by ECD center staff trained and supported by Save the Children, with ALL resident children eligible to participate in the interventions irrespective of enrolment in ECD program (ECD Control group).

2) Children living in villages in the intervention arm also received the SMC and parenting interventions described above, but additionally were eligible to receive home supplementation with micronutrient powders (MNP intervention arm).

3) Second, a third non-randomised arm was recruited comprised of children living in 30 randomly selected villages where there were no ECD centers in place and thus both the parenting interventions and MNPs were absent. These children received SMC only, as part of national health programming (non-ECD comparison arm).

Trial arm and Interventions received:

T1. MNP intervention arm: 30 villages with ECD centre (randomised); MNP-Yes, Parenting-Yes, SMC-Yes C1. ECD control arm: 30 villages with ECD centre (randomised); MNP-No, Parenting-Yes, SMC-Yes C2. Non-ECD comparison arm: 30 villages without ECD centre (not randomised); MNP-No, Parenting-No, SMC-Yes

Three cross-sectional endline surveys took place during the period May-August 2016, three years after the original MNP intervention began, and consisted of the following questionnaires and assessments in two age groups of children, 3 year olds and 5 year olds:

i) A household questionnaire was used to collect data from the primary adult caregiver of the child on home environment, exposure to the interventions, and reported practice outcomes of relevance to the parenting intervention.

ii) Biomedical outcomes were measured in children through laboratory and clinical assessment.

iii) A battery of tests were used to assess cognitive performance and school readiness in childen, using a different age-specific test battery for each age group adapted for local language and culture.

Note: Household and cognitive performance data were gathered from participants in all three arms. Biomedical data were only collected from children in the two randomised arms, to evaluate impact of MNP supplementation on anaemia (primary biomedical outcome) in children who received MNPs and those who did not, using a robust study design.

Geographic coverage

Districts (cercles) of Sikasso and Yorosso, Region of Sikasso

Analysis unit

Individuals and communities

Universe

Random sample of target population for the intervention in the 90 communities that consented to participate in the trial, namely pre-school children 0-6 years.

Kind of data

Sample survey data [ssd]

Sampling procedure

The target population for the interventions comprised all children aged 3 months to 6 years, who were resident in the 90 study communities participating in the trial; the primary sampling unit is the individual child.

Sample Frame:

To identify the number of target beneficiaries, a complete census of all children of eligible age was carried out in the 90 study villages in August 2013. The census listing from 2013 thus defined the population of children who are eligible to have received the interventions every year for the three years between 2013-2016; and was used as the sampling frame of children in whom the impact after three years of implementation of the interventions was evaluated. The intention was to evaluate study outcomes in the same child one year after the start of the MNP intervention (May 2014) and again after three years of the intervention (2016).

A random sample of children was drawn from all children listed in the census for each community participating in the trial, according to the following age criteria:

Date of Birth, or Age in August 2013 (Age group in 2016 surveys) (i) Born between 1 Jan 2013 – 30 June 2013, or aged <1 year in 2013 census if DOB not known (3 years) (ii) Born between 1 May 2010 – 30 April 2011, or aged 2 years in census if DOB not known (5 years)

Thus, all children previously randomly selected and enrolled in the evaluation cohort in 2014 were, if still resident in the village and present on the day of the survey, re-surveyed in May 2016.

Sample Size:

Power analysis was undertaken for a comparison of two arms, taking account of clustering by community. Survey data on biomedical and cognitive outcomes collected in 2014 were used to inform sample size assumptions, including prevalence of primary outcomes, intraclass correlation (ICC) and number of children recruited per cluster. Prevalence of anaemia amongst 3-year old children in 2014 was found to be 61.6% and 64.0% in the intervention and control arms respectively (p=0.618) and 53.8% and 51.9% respectively amongst 5-year old children (p=0.582). The observed ICC for anaemia endpoint at baseline was 0.08 in 3-year old children and 0.06 in 5-year old children. Observed ICC for cognitive outcomes measured in 2014 was 0.09, ranging from 0.05 to 0.16 for individual tasks within the cognitive battery.

Sample Size Estimation for Health Outcomes:

Approximately 20-25 children per cluster were recruited into each age cohort in 2013. Power calculations for anaemia (primary endpoint) were undertaken for three alternative scenarios at endline: (i) to allow for the possibility of up to 20% loss to follow up between 2014 and 2016, power calculations were performed for a sample size at endline of 16 children per cluster; (ii) a smaller cluster size of 14 children sampled per village, under a scenario of 30% loss to follow-up; and (iii) unequal clusters, to allow for the possibility that variation in losses to follow-up between villages could result in an unequal number of children sampled in each village. In this case, cluster size is the mean number of children sampled per cluster.

Thus, assuming a conservative prevalence of anaemia of 50% in the control group and ICC of 0.08, a sample size of 30 communities per arm with 14-20 children sampled per community, will under all of these scenarios provide 80% power to detect a reduction in anemia of at least 28% at 5% level of significance.

Sample Size Estimation for Cognitive Outcomes:

Power calculations for cognitive outcomes explored: (i) a smaller cluster size of 14 children sampled per village, for example resulting from a higher than expected loss to follow-up of 30%; (ii) statistical analysis of differences between arms which does not adjust for baseline - a scenario which allows for the possibility to increase the sample size to compensate for losses to follow-up by increased recruitment of new children for whom no baseline data would be available; and (iii) effect of unequal clusters. Thus, for cognitive-linguistic skills, a sample size of 30 communities per arm with 14-20 children in each age cohort sampled per community will provide 80% power to detect an effect size between 0.27-0.29 at 5% level of significance, assuming an (ICC) of 0.10 and individual, household and community-level factors account for at least 25% of variation in cognitive foundation skills. Whilst for a similar sample size of 30 communities per arm with 14-20 children sampled per community and ICC of 0.10, a statistical analysis which does not adjust for baseline will provide 80% power to detect an effect size between 0.28-0.30 at 5% level of significance.

The sample at endline in May 2016 thus comprised a total of up to 600 children aged 3y and 600 children aged 5y at endline in each arm: T1 Intervention group (with ECD): 30 communities, with approx. 40 randomly selected children in each community (20 aged 3y; 20 aged 5y). C1 ECD control group (with ECD): 30 communities, with approx. 40 randomly selected children in each community (20 aged 3y; 20 aged 5y). C2 Comparison group (without ECD): 30 communities, with approx. 40 randomly selected children in each community (20 aged 3y; 20 aged 5y).

Strategy for Absent Respondents/Not Found/Refusals:

Every effort was made to trace children previously recruited into the evaluation cohort. Since some losses-to-follow-up (for example to due to child deaths, outward migration) were expected between 2014 and 2016, the primary strategy was to oversample in 2014. However, for villages where loss-to-follow-up was higher than expected and it was not possible to trace sufficient number of children remaining from the original sample to meet the required sample size per cluster, additional children were recruited into the evaluation survey in 2016. New recruits were selected at random from the children listed as resident in the village at the time of the original census in 2013. All new recruits had thus been resident in the village and exposed to the interventions throughout the three preceding years.

Mode of data collection

Face-to-face [f2f]

Research instrument

1. Household questionnaire (Form_Parent_MaliSIEF_2016_french.pdf ; Form_Parent_MaliSIEF_2016_english.pdf)

The questionnaires for the parent interview were structured questionnaires. A questionnaire was administered to the child’s primary caregiver

A random sample of households were invited to participate in this survey. In the dataset, you will find the respondent level data in each row with the questions in each column. The numbers represent a scale option from the survey, such as 1=Excellent, 2=Good, 3=Fair, 4=Poor. The question stem, response option, and scale information for each field can be found in the var "variable labels" and "value labels" sheets. VERY IMPORTANT NOTE: The scientific survey data were weighted, meaning that the demographic profile of respondents was compared to the demographic profile of adults in Bloomington from US Census data. Statistical adjustments were made to bring the respondent profile into balance with the population profile. This means that some records were given more "weight" and some records were given less weight. The weights that were applied are found in the field "wt". If you do not apply these weights, you will not obtain the same results as can be found in the report delivered to the Bloomington. The easiest way to replicate these results is likely to create pivot tables, and use the sum of the "wt" field rather than a count of responses.

Abstract

The main purpose of a Household Income and Expenditure Survey (HIES) was to present high quality and representative national household data on income and expenditure in order to update Consumer Price Index (CPI), improve statistics on National Accounts and measure poverty within the country.

The main objectives of this survey - update the weight of each expenditure item (from COICOP) and obtain weights for the revision of the Consumer Price Index (CPI) for Funafuti - provide data on the household sectors contribution to the National Accounts - design the structure of consumption for food secutiry - To provide information on the nature and distribution of household income, expenditure and food consumption patterns household living standard useful for planning purposes - To provide information on economic activity of men and women to study gender issues - To generate the income distribution for poverty analysis

The 2010 Household Income and Expenditure Survey (HIES) is the third HIES that was conducted by the Central Statistics Division since Tuvalu gained political independence in 1978.

This survey deals mostly with expenditure and income on the cash side and non cash side (gift, home production). Moreover, a lot of information are collected:

at a household level: - goods possession - description of the dwelling - water tank capacity - fruits and vegetables in the garden - livestock

at an individual level: - education level - employment - health

Geographic coverage

National Coverage: Funafuti and /Outer islands.

Analysis unit

• Household level
• Individual level

Universe

The scope of the 2010 Household Income and Expenditure Survey (HIES) was all occupied households in Tuvalu. Households are the sampling unit, defined as a group of people (related or not) who pool their money, and cook and eat together. It is not the physical structure (dwelling) in which people live. HIES covered all persons who were considered to be usual residents of private dwellings (must have been living in Tuvalu for a period of 12-months, or have intention to live in Tuvalu for a period of 12-months in order to be included in the survey). Usual residents who are temporary away are included as well (e.g., for work or a holiday).

All the private household are included in the sampling frame. In each household selected, the current resident are surveyed, and people who are usual resident but are currently away (work, health, holydays reasons, or border student for example. If the household had been residing in Tuvalu for less than one year: - but intend to reside more than 12 months => he is included - do not intend to reside more than 12 months => out of scope.

Kind of data

Sample survey data [ssd]

Sampling procedure

The Tuvalu 2010 Household Income and Expenditure Survey (HIES) outputs breakdowns at the domain level which is Funafuti and Outer Islands. To achieve this, and to match the budget constraint, a third of the households were selected in both domains. It was decided that 33% (one third) sample was sufficient to achieve suitable levels of accuracy for key estimates in the survey. So the sample selection was spread proportionally across all the islands except Niulakita as it was considered too small. The selection method used is the simple random survey, meaning that within each domain households were directly selected from the population frame (which was the updated 2009 household listing). All islands were included in the selection except Niulakita that was excluded due to its remoteness, and size.

For selection purposes, in the outer island domain, each island was treated as a separate strata and independent samples were selected from each (one third). The strategy used was to list each dwelling on the island by their geographical position and run a systematic skip through the list to achieve the 33% sample. This approach assured that the sample would be spread out across each island as much as possible and thus more representative.

Population and sample counts of dwellings by islands for 2010 HIES Islands: -Nanumea: Population: 123; sample: 41 -Nanumaga: Population: 117; sample: 39 -Niutao: Population: 138; sample: 46 -Nui: Population: 141; sample: 47 -Vaitupu: Population: 298; sample: 100 -Nukufetau: Population: 141; sample: 47 -Nukulaelae: Population: 78; sample: 26 -Funafuti: Population: 791; sample: 254 -TOTAL: Population: 1827; sample: 600.

Mode of data collection

Face-to-face [f2f]

Research instrument

3 forms were used. Each question is writen in English and translated in Tuvaluan on the same version of the questionnaire. The questionnaire was highly based on the previous one (2004 survey).

Household Schedule This questionnaire, to be completed by interviewers, is used to collect information about the household composition, living conditions and is also the main form for collecting expenditure on goods and services purchased infrequently.

• composition of the household and demographic profile of each members
• dwelling information
• dwelling expenditure
• transport expenditure
• education expenditure
• health expenditure
• land and property expenditure
• household furnishing
• home appliances
• cultural and social payments
• holydays/travel costs
• Loans and saving
• clothing
• other major expenditure items

Individual Schedule There will be two individual schedules: - health and education - labor force (individual aged 15 and above) - employment activity and income (individual aged 15 and above): wages and salaries working own business agriculture and livestock fishing income from handicraft income from gambling small scale activies jobs in the last 12 months other income childreen income tobacco and alcohol use other activities seafarer

Diary (one diary per week, on a 2 weeks period, 2 diaries per household were required) The diaries are used to record all household expenditure and consumption over the two week diary keeping period. The diaries are to be filled in by the household members, with the assistance from interviewers when necessary. - All kind of expenses - Home production - food and drink (eaten by the household, given away, sold) - Goods taken from own business (consumed, given away) - Monetary gift (given away, received, winning from gambling) - Non monetary gift (given away, received, winning from gambling).

Cleaning operations

Consistency of the data: - each questionnaire was checked by the supervisor during and after the collection - before data entry, all the questionnaire were coded - the CSPRo data entry system included inconsistency checks which allow the National Statistics Office staff to point some errors and to correct them with imputation estimation from their own knowledge (no time for double entry), 4 data entry operators. 1. presence of all the form for each household 2. consistency of data within the questionnaire

at this stage, all the errors were corrected on the questionnaire and on the data entry system in the meantime.

• after data entry, the extreme amount of each questionnaire where selected in order to check their consistency. at this stage, all the inconsistency were corrected by imputation on CSPRO editing.

Response rate

The final response rates for the survey was very pleasing with an average rate of 97 per cent across all islands selected. The response rates were derived by dividing the number of fully responding households by the number of selected households in scope of the survey which weren't vacant.

Response rates for Tuvalu 2010 Household Income and Expenditure Survey (HIES): - Nanumea 100% - Nanumaga 100% - Niutao 98% - Nui 100% - Vaitupu 99% - Nukufetau 89% - Nukulaelae 100% - Funafuti 96%

As can be seen in the table, four of the islands managed a 100 per cent response, whereas only Nukufetau had a response rate of less than 90 per cent.

Further explanation of response rates can be located in the external resource entitled Tuvalu 2010 HIES Report Table 1.2.

Sampling error estimates

The quality of the results can be found in the report provided in this documentation.

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

The 1998 Ghana Demographic and Health Survey (GDHS) is the latest in a series of national-level population and health surveys conducted in Ghana and it is part of the worldwide MEASURE DHS+ Project, designed to collect data on fertility, family planning, and maternal and child health.

The primary objective of the 1998 GDHS is to provide current and reliable data on fertility and family planning behaviour, child mortality, children’s nutritional status, and the utilisation of maternal and child health services in Ghana. Additional data on knowledge of HIV/AIDS are also provided. This information is essential for informed policy decisions, planning and monitoring and evaluation of programmes at both the national and local government levels.

The long-term objectives of the survey include strengthening the technical capacity of the Ghana Statistical Service (GSS) to plan, conduct, process, and analyse the results of complex national sample surveys. Moreover, the 1998 GDHS provides comparable data for long-term trend analyses within Ghana, since it is the third in a series of demographic and health surveys implemented by the same organisation, using similar data collection procedures. The GDHS also contributes to the ever-growing international database on demographic and health-related variables.

Geographic coverage

National

Analysis unit

• Household
• Children under five years
• Women age 15-49
• Men age 15-59

Kind of data

Sample survey data

Sampling procedure

The major focus of the 1998 GDHS was to provide updated estimates of important population and health indicators including fertility and mortality rates for the country as a whole and for urban and rural areas separately. In addition, the sample was designed to provide estimates of key variables for the ten regions in the country.

The list of Enumeration Areas (EAs) with population and household information from the 1984 Population Census was used as the sampling frame for the survey. The 1998 GDHS is based on a two-stage stratified nationally representative sample of households. At the first stage of sampling, 400 EAs were selected using systematic sampling with probability proportional to size (PPS-Method). The selected EAs comprised 138 in the urban areas and 262 in the rural areas. A complete household listing operation was then carried out in all the selected EAs to provide a sampling frame for the second stage selection of households. At the second stage of sampling, a systematic sample of 15 households per EA was selected in all regions, except in the Northern, Upper West and Upper East Regions. In order to obtain adequate numbers of households to provide reliable estimates of key demographic and health variables in these three regions, the number of households in each selected EA in the Northern, Upper West and Upper East regions was increased to 20. The sample was weighted to adjust for over sampling in the three northern regions (Northern, Upper East and Upper West), in relation to the other regions. Sample weights were used to compensate for the unequal probability of selection between geographically defined strata.

The survey was designed to obtain completed interviews of 4,500 women age 15-49. In addition, all males age 15-59 in every third selected household were interviewed, to obtain a target of 1,500 men. In order to take cognisance of non-response, a total of 6,375 households nation-wide were selected.

Note: See detailed description of sample design in APPENDIX A of the survey report.

Mode of data collection

Face-to-face

Research instrument

Three types of questionnaires were used in the GDHS: the Household Questionnaire, the Women’s Questionnaire, and the Men’s Questionnaire. These questionnaires were based on model survey instruments developed for the international MEASURE DHS+ programme and were designed to provide information needed by health and family planning programme managers and policy makers. The questionnaires were adapted to the situation in Ghana and a number of questions pertaining to on-going health and family planning programmes were added. These questionnaires were developed in English and translated into five major local languages (Akan, Ga, Ewe, Hausa, and Dagbani).

The Household Questionnaire was used to enumerate all usual members and visitors in a selected household and to collect information on the socio-economic status of the household. The first part of the Household Questionnaire collected information on the relationship to the household head, residence, sex, age, marital status, and education of each usual resident or visitor. This information was used to identify women and men who were eligible for the individual interview. For this purpose, all women age 15-49, and all men age 15-59 in every third household, whether usual residents of a selected household or visitors who slept in a selected household the night before the interview, were deemed eligible and interviewed. The Household Questionnaire also provides basic demographic data for Ghanaian households. The second part of the Household Questionnaire contained questions on the dwelling unit, such as the number of rooms, the flooring material, the source of water and the type of toilet facilities, and on the ownership of a variety of consumer goods.

The Women’s Questionnaire was used to collect information on the following topics: respondent’s background characteristics, reproductive history, contraceptive knowledge and use, antenatal, delivery and postnatal care, infant feeding practices, child immunisation and health, marriage, fertility preferences and attitudes about family planning, husband’s background characteristics, women’s work, knowledge of HIV/AIDS and STDs, as well as anthropometric measurements of children and mothers.

The Men’s Questionnaire collected information on respondent’s background characteristics, reproduction, contraceptive knowledge and use, marriage, fertility preferences and attitudes about family planning, as well as knowledge of HIV/AIDS and STDs.

Response rate

A total of 6,375 households were selected for the GDHS sample. Of these, 6,055 were occupied. Interviews were completed for 6,003 households, which represent 99 percent of the occupied households. A total of 4,970 eligible women from these households and 1,596 eligible men from every third household were identified for the individual interviews. Interviews were successfully completed for 4,843 women or 97 percent and 1,546 men or 97 percent. The principal reason for nonresponse among individual women and men was the failure of interviewers to find them at home despite repeated callbacks.

Note: See summarized response rates by place of residence in Table 1.1 of the survey report.

Sampling error estimates

The estimates from a sample survey are affected by two types of errors: (1) nonsampling errors, and (2) sampling errors. Nonsampling errors are the results of shortfalls made in implementing data collection and data processing, such as failure to locate and interview the correct household, misunderstanding of the questions on the part of either the interviewer or the respondent, and data entry errors. Although numerous efforts were made during the implementation of the 1998 GDHS to minimize this type of error, nonsampling errors are impossible to avoid and difficult to evaluate statistically.

Sampling errors, on the other hand, can be evaluated statistically. The sample of respondents selected in the 1998 GDHS is only one of many samples that could have been selected from the same population, using the same design and expected size. Each of these samples would yield results that differ somewhat from the results of the actual sample selected. Sampling errors are a measure of the variability between all possible samples. Although the degree of variability is not known exactly, it can be estimated from the survey results.

A sampling error is usually measured in terms of the standard error for a particular statistic (mean, percentage, etc.), which is the square root of the variance. The standard error can be used to calculate confidence intervals within which the true value for the population can reasonably be assumed to fall. For example, for any given statistic calculated from a sample survey, the value of that statistic will fall within a range of plus or minus two times the standard error of that statistic in 95 percent of all possible samples of identical size and design.

If the sample of respondents had been selected as a simple random sample, it would have been possible to use straightforward formulas for calculating sampling errors. However, the 1998 GDHS sample is the result of a two-stage stratified design, and, consequently, it was necessary to use more complex formulae. The computer software used to calculate sampling errors for the 1998 GDHS is the ISSA Sampling Error Module. This module uses the Taylor linearization method of variance estimation for survey estimates that are means or proportions. The Jackknife repeated replication method is used for variance estimation of more complex statistics such as fertility and mortality rates.

Data appraisal

Data Quality Tables - Household age distribution - Age distribution of eligible and interviewed women - Age distribution of eligible and interviewed men - Completeness of reporting - Births by calendar years - Reporting of age at death in days - Reporting of age at death in months

Note: See detailed tables in APPENDIX C of the survey report.

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

This dataset was developed by the Research & Analytics Group at the Atlanta Regional Commission using data from the U.S. Census Bureau.For a deep dive into the data model including every specific metric, see the Infrastructure Manifest. The manifest details ARC-defined naming conventions, field names/descriptions and topics, summary levels; source tables; notes and so forth for all metrics.Naming conventions:Prefixes: None Countp Percentr Ratem Mediana Mean (average)t Aggregate (total)ch Change in absolute terms (value in t2 - value in t1)pch Percent change ((value in t2 - value in t1) / value in t1)chp Change in percent (percent in t2 - percent in t1)s Significance flag for change: 1 = statistically significant with a 90% CI, 0 = not statistically significant, blank = cannot be computed Suffixes: _e19 Estimate from 2014-19 ACS_m19 Margin of Error from 2014-19 ACS_00_v19 Decennial 2000, re-estimated to 2019 geography_00_19 Change, 2000-19_e10_v19 2006-10 ACS, re-estimated to 2019 geography_m10_v19 Margin of Error from 2006-10 ACS, re-estimated to 2019 geography_e10_19 Change, 2010-19The user should note that American Community Survey data represent estimates derived from a surveyed sample of the population, which creates some level of uncertainty, as opposed to an exact measure of the entire population (the full census count is only conducted once every 10 years and does not cover as many detailed characteristics of the population). Therefore, any measure reported by ACS should not be taken as an exact number – this is why a corresponding margin of error (MOE) is also given for ACS measures. The size of the MOE relative to its corresponding estimate value provides an indication of confidence in the accuracy of each estimate. Each MOE is expressed in the same units as its corresponding measure; for example, if the estimate value is expressed as a number, then its MOE will also be a number; if the estimate value is expressed as a percent, then its MOE will also be a percent. The user should also note that for relatively small geographic areas, such as census tracts shown here, ACS only releases combined 5-year estimates, meaning these estimates represent rolling averages of survey results that were collected over a 5-year span (in this case 2015-2019). Therefore, these data do not represent any one specific point in time or even one specific year. For geographic areas with larger populations, 3-year and 1-year estimates are also available. For further explanation of ACS estimates and margin of error, visit Census ACS website.Source: U.S. Census Bureau, Atlanta Regional CommissionDate: 2015-2019Data License: Creative Commons Attribution 4.0 International (CC by 4.0)Link to the manifest: https://www.arcgis.com/sharing/rest/content/items/3d489c725bb24f52a987b302147c46ee/data

Supporting documentation on code lists, subject definitions, data accuracy, and statistical testing can be found on the American Community Survey website in the Data and Documentation section...Sample size and data quality measures (including coverage rates, allocation rates, and response rates) can be found on the American Community Survey website in the Methodology section..Although the American Community Survey (ACS) produces population, demographic and housing unit estimates, it is the Census Bureau''s Population Estimates Program that produces and disseminates the official estimates of the population for the nation, states, counties, cities and towns and estimates of housing units for states and counties..Explanation of Symbols:An ''**'' entry in the margin of error column indicates that either no sample observations or too few sample observations were available to compute a standard error and thus the margin of error. A statistical test is not appropriate..An ''-'' entry in the estimate column indicates that either no sample observations or too few sample observations were available to compute an estimate, or a ratio of medians cannot be calculated because one or both of the median estimates falls in the lowest interval or upper interval of an open-ended distribution..An ''-'' following a median estimate means the median falls in the lowest interval of an open-ended distribution..An ''+'' following a median estimate means the median falls in the upper interval of an open-ended distribution..An ''***'' entry in the margin of error column indicates that the median falls in the lowest interval or upper interval of an open-ended distribution. A statistical test is not appropriate..An ''*****'' entry in the margin of error column indicates that the estimate is controlled. A statistical test for sampling variability is not appropriate. .An ''N'' entry in the estimate and margin of error columns indicates that data for this geographic area cannot be displayed because the number of sample cases is too small..An ''(X)'' means that the estimate is not applicable or not available..Estimates of urban and rural population, housing units, and characteristics reflect boundaries of urban areas defined based on Census 2010 data. As a result, data for urban and rural areas from the ACS do not necessarily reflect the results of ongoing urbanization..While the 2013 American Community Survey (ACS) data generally reflect the February 2013 Office of Management and Budget (OMB) definitions of metropolitan and micropolitan statistical areas; in certain instances the names, codes, and boundaries of the principal cities shown in ACS tables may differ from the OMB definitions due to differences in the effective dates of the geographic entities..Due to methodological changes to data collection for data year 2013, comparisons of current-year language estimates to past years' language estimates should be made with caution. For more information, see: http://www.census.gov/acs/www/data_documentation/user_notes/.A "limited English speaking household" is one in which no member 14 years old and over (1) speaks only English or (2) speaks a non-English language and speaks English "very well." In other words, all members 14 years old and over have at least some difficulty with English. By definition, English-only households cannot belong to this group. Previous Census Bureau data products have referred to these households as "linguistically isolated" and "Households in which no one 14 and over speaks English only or speaks a language other than English at home and speaks English 'very well'." This table is directly comparable to tables from earlier years that used these labels..In data year 2013, there were a series of changes to data collection operations that could have affected some estimates. These changes include the addition of Internet as a mode of data collection, the end of the content portion of Failed Edit Follow-Up interviewing, and the loss of one monthly panel due to the Federal Government shut down in October 2013. For more information, see: User Notes.Data are based on a sample and are subject to sampling variability. The degree of uncertainty for an estimate arising from sampling variability is represented through the use of a margin of error. The value shown here is the 90 percent margin of error. The margin of error can be interpreted roughly as providing a 90 percent probability that the interval defined by the estimate minus the margin of error and the estimate plus the margin of error (the lower and upper confidence bounds) contains the true value. In addition to sampling variability, the ACS estimates are subject to nonsampling error (for a discussion of nonsampling variability, see Accuracy of the Data). The effect of nonsampling error is not represented in these tables..Source: U.S. Census Bureau, 2013 American Community Survey

The mid-year estimates refer to the population on 30 June of the reference year and are produced in line with the standard United Nations (UN) definition for population estimates. They are the official set of population estimates for the UK and its constituent countries, the regions and counties of England, and local authorities and their equivalents.

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which