Abstract

The Annual Household Income and Expenditure Survey (AHIES) is the first nationally representative high-frequency household panel survey in Ghana. The AHIES is being conducted to obtain quarterly and annual data on household final consumption expenditure and a wide scope of demographic, economic and welfare variables including statistics on labour, food security, multi-dimensional poverty and health status for research, policy, and planning. Some of the key macroeconomic indicators to be generated include quarterly GDP, regional GDP, quarterly unemployment, underemployment, inequality, consumption expenditure poverty, multidimensional poverty and food security. The data from the AHIES is classified, tabulated and disseminated so that researchers, administrators, policy makers and development partners can use the information in formulating and implementing various development programs at the national and community levels and also to monitor targets under the Sustainable Development Goals.

Geographic coverage

Nation - Wide

Analysis unit

Individuals, Households

Universe

The universe covers the population living within individual households in Ghana. However, such population which is defined as institutionalised population as persons living at elderly houses, rest homes, correction facilities, military baracks, and hospitals with special characteristics, nursery,and also nomadic population are excluded.

Sampling procedure

With the sampling procedure, 10,800 households in 600 EAs, consisting of 304 (50.67%) urban and 296 (49.33%) rural households were drawn from the 2021 Population and Housing Census listing frame to form the secondary sampling units. A random sampling methodology was adopted to select eighteen (18) households per selected EAs in all regions to form the full sample for the fieldwork to be able to produce regionally representative expenditures for GDP.

Mode of data collection

Computer Assisted Personal Interview [CAPI]

Abstract

To facilitate the use of data collected through the high-frequency phone surveys on COVID-19, the Living Standards Measurement Study (LSMS) team has created the harmonized datafiles using two household surveys: 1) the country’ latest face-to-face survey which has become the sample frame for the phone survey, and 2) the country’s high-frequency phone survey on COVID-19.

The LSMS team has extracted and harmonized variables from these surveys, based on the harmonized definitions and ensuring the same variable names. These variables include demography as well as housing, household consumption expenditure, food security, and agriculture. Inevitably, many of the original variables are collected using questions that are asked differently. The harmonized datafiles include the best available variables with harmonized definitions.

Two harmonized datafiles are prepared for each survey. The two datafiles are: 1. HH: This datafile contains household-level variables. The information include basic household characterizes, housing, water and sanitation, asset ownership, consumption expenditure, consumption quintile, food security, livestock ownership. It also contains information on agricultural activities such as crop cultivation, use of organic and inorganic fertilizer, hired labor, use of tractor and crop sales. 2. IND: This datafile contains individual-level variables. It includes basic characteristics of individuals such as age, sex, marital status, disability status, literacy, education and work.

Geographic coverage

National coverage

Analysis unit

• Households
• Individuals

Universe

The survey covered all de jure households excluding prisons, hospitals, military barracks, and school dormitories.

Kind of data

Sample survey data [ssd]

Sampling procedure

See “Ethiopia - Socioeconomic Survey 2018-2019” and “Ethiopia - COVID-19 High Frequency Phone Survey of Households 2020” available in the Microdata Library for details.

Mode of data collection

Computer Assisted Personal Interview [capi]

Cleaning operations

Ethiopia Socioeconomic Survey (ESS) 2018-2019 and Ethiopia COVID-19 High Frequency Phone Survey of Households (HFPS) 2020 data were harmonized following the harmonization guidelines (see “Harmonized Datafiles and Variables for High-Frequency Phone Surveys on COVID-19” for more details).

The high-frequency phone survey on COVID-19 has multiple rounds of data collection. When variables are extracted from multiple rounds of the survey, the originating round of the survey is noted with “_rX” in the variable name, where X represents the number of the round. For example, a variable with “_r3” presents that the variable was extracted from Round 3 of the high-frequency phone survey. Round 0 refers to the country’s latest face-to-face survey which has become the sample frame for the high-frequency phone surveys on COVID-19. When the variables are without “_rX”, they were extracted from Round 0.

Response rate

See “Ethiopia - Socioeconomic Survey 2018-2019” and “Ethiopia - COVID-19 High Frequency Phone Survey of Households 2020” available in the Microdata Library for details.

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Abstract

Household Expenditure Survey 2009/10 was used to compile information on the level and patterns of consumption expenditure of private households. It was also used to update the weighting patterns and to determine the items in the basket of goods and services for the compilation of the Consumer Price Index for Malaysia.

The objectives of HES are to: - gather information on the level and pattern of consumption expenditure by household on a comprehensive range of goods and services; - determine the goods and services to be included in the basket of the Consumer Price Index (CPI); - update the CPI weights which is a measure of inflation rate in the country.

Geographic coverage

The survey covered both urban and rural areas in Malaysia except the Orang Asli Enumeration Block (EBs) in Peninsular Malaysia. Usually the EBs that lie in the interior areas are not included in the sampling frames. However, for the latest HES, the Department had expanded its coverage to include these EBs.

Analysis unit

• Households
• Individuals

Universe

The survey only covered households staying in private living quarters (LQ). The institutional households, that is, those living in hostels, hotels, hospitals, old folks homes, military and police barracks, prisons, welfare homes and other institutions were excluded from the coverage of the survey.

Kind of data

Sample survey data [ssd]

Frequency of data collection

Once in 5 years

Sampling procedure

Sampling Frame The frame for HES 2009/10 sample selection was based on the National Household Sampling Frame (NHSF) which was made up of EBs created for the 2000 Population and Housing Census. EBs are geographically contiguous areas of land with identifiable boundaries. On average, each EB contains about 80-120 LQs. Generally, all EBs are formed within gazetted boundaries, i.e. within administrative district, mukim or local authority areas.

The EBs in the sampling frame were also classified by urban and rural areas. Urban areas were as defined in the 2000 Population and Housing Census. Urban areas are gazetted areas with their adjoining built-up areas which has a combined population of 10,000 or more at the time of 2000 Population and Housing Census. All other gazetted areas with a population of less than 10,000 persons and non-gazetted areas are classified as rural. Built-up areas are defined as areas contiguous to a gazetted area and has at least 60 per cent of their population (aged 10 years and over) engaged in non-agricultural activities as well as having modern toilet facilities in their housing units.

Urbanisation is a dynamic process and keeps changing in line with progress and development. Thus, urban areas for the 1991 and 2000 censuses may not necessarily refer to the same areas, as these urban areas continue to increase and grow over time.

The classification of areas by stratum is as follows:

Stratum     Number of Population
(a) Metropolitan    75,000 and over
(b) Urban Large   10,000 to 74,999
(c) Urban Small   1,000 to 9,999
(d) Rural    All other areas

For sampling purposes, the above broad classification was found to be adequate for all states and W.P. Kuala Lumpur, Putrajaya and Labuan. However, for Sabah and Sarawak, due to inaccessibility, the rural stratum had to be further stratified based on the time taken to reach the area from the nearest urban centre.

For purposes of tabulation by urban and rural, the strata were combined as follows: Metropolitan + urban large = Urban Urban small + all rural = Rural

Sampling Design A two-stage stratified sampling design was adopted and the level of stratification is as follows: Primary stratum - made up of the states in Malaysia, including W.P. Kuala Lumpur, Putrajaya and Labuan. Secondary stratum - made up of selected towns, others towns and rural stratum formed within the primary stratum.

Mode of data collection

Face-to-face [f2f]

Sampling error estimates

Data obtained from surveys or research based on probability sample may encounter two types of errors, i.e. sampling and non-sampling errors.

Sampling Error Sampling error is a result of estimating data based on probability sampling, not on census. Statistically, these errors are referred to as Relative Standard Errors, denoted by RSE and expressed in percentage. This error is an indication of the precision of the parameter under study. In other words, it reflects the extent of variation as compared with other sample-based estimates.

For HES 2009/10, the average monthly household expenditure for Malaysia is RM2,190 with RSE 1.2 per cent. In absolute terms, the standard error (SE) is approximately RM26. With the assumption that the average monthly household expenditure is normally distributed, the confidence interval for the estimated average monthly household expenditure can be calculated. Based on a 95 percent confidence level (alpha=0.05), the average monthly household expenditure was found to be in the range of RM2,139-RM2,241 per month.

Non-sampling Error To ensure high quality data, several steps were taken to minimise non-sampling errors. Unlike sampling errors, these errors cannot be measured and can only be overcome through several administrative procedures. These errors may arise as a result of incomplete survey coverage, weakness in the frame, feedback errors, non-response errors, errors during data processing such as editing, coding and data capture.

Response errors are likely to occur due to differences and difficulties in interpreting the questions, be it on the part of the enumerators or respondents. To minimise these errors, intensive trainings were conducted for the enumerators as well as for the supervisors. In addition, random checks were carried out on households that were already canvassed by the enumerators to verify the validity of the information recorded. To ensure the completeness of the survey coverage, the sampling frame is frequently updated and the LQs were selected after the completion of EB listing exercise.

For HES 2009/10, there were no substitution for non-response cases, such as refusal to co-operate or no one at home. The calculation of weights was based on actual responses. In order to obtain respondents' co-operation, a wide scale publicity of the survey was launched through the electronic and print media. To reduce the editing and processing errors, several consistency checks were created, either manually or computer aided, to ensure the quality and reliability of data.

Abstract

To facilitate the use of data collected through the high-frequency phone surveys on COVID-19, the Living Standards Measurement Study (LSMS) team has created the harmonized datafiles using two household surveys: 1) the country’ latest face-to-face survey which has become the sample frame for the phone survey, and 2) the country’s high-frequency phone survey on COVID-19.

The LSMS team has extracted and harmonized variables from these surveys, based on the harmonized definitions and ensuring the same variable names. These variables include demography as well as housing, household consumption expenditure, food security, and agriculture. Inevitably, many of the original variables are collected using questions that are asked differently. The harmonized datafiles include the best available variables with harmonized definitions.

Two harmonized datafiles are prepared for each survey. The two datafiles are: 1. HH: This datafile contains household-level variables. The information include basic household characterizes, housing, water and sanitation, asset ownership, consumption expenditure, consumption quintile, food security, livestock ownership. It also contains information on agricultural activities such as crop cultivation, use of organic and inorganic fertilizer, hired labor, use of tractor and crop sales.
2. IND: This datafile contains individual-level variables. It includes basic characteristics of individuals such as age, sex, marital status, disability status, literacy, education and work.

Geographic coverage

National coverage

Analysis unit

• Households
• Individuals

Universe

The survey covered all de jure households excluding prisons, hospitals, military barracks, and school dormitories.

Kind of data

Sample survey data [ssd]

Sampling procedure

See “Malawi - Integrated Household Panel Survey 2010-2013-2016-2019 (Long-Term Panel, 102 EAs)” and “Malawi - High-Frequency Phone Survey on COVID-19” available in the Microdata Library for details.

Mode of data collection

Computer Assisted Personal Interview [capi]

Cleaning operations

Malawi Integrated Household Panel Survey (IHPS) 2019 and Malawi High-Frequency Phone Survey on COVID-19 data were harmonized following the harmonization guidelines (see “Harmonized Datafiles and Variables for High-Frequency Phone Surveys on COVID-19” for more details).

The high-frequency phone survey on COVID-19 has multiple rounds of data collection. When variables are extracted from multiple rounds of the survey, the originating round of the survey is noted with “_rX” in the variable name, where X represents the number of the round. For example, a variable with “_r3” presents that the variable was extracted from Round 3 of the high-frequency phone survey. Round 0 refers to the country’s latest face-to-face survey which has become the sample frame for the high-frequency phone surveys on COVID-19. When the variables are without “_rX”, they were extracted from Round 0.

Response rate

See “Malawi - Integrated Household Panel Survey 2010-2013-2016-2019 (Long-Term Panel, 102 EAs)” and “Malawi - High-Frequency Phone Survey on COVID-19” available in the Microdata Library for details.

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Abstract

SUSENAS (National Socio-economic Survey) was held for the first time in year 1963. In the last two decades, up to year 2010, SUSENAS was conducted every year. SUSENAS was designed to have 3 modules (Module of Household Consumption/Expenditure, Module of Education and Socio-culture, and also Module of Health and Housing) and each module should be conducted every 3 years. Household Consumption/ Expenditure Module of SUSENAS shall be conducted in year 2011.

To improve the accuracy of data result and in line with the increased frequency of household consumption/expenditure data request for quarterly GDP/GRDP and poverty calculation, data collection of household consumption/expenditure, it is planned that starting in 2011 it should be held quarterly. Each year, collecting data shall be conducted in March, June, September, and December.

In accordance with the 5-year cycle, in year 2012, BPS (Central Statistical Agency) shall have planned Survei Biaya Hidup-SBH (Cost of Living Survey) with the aim to generate a commodity package and a weigh diagram in the calculation of Consumer Price Index (CPI). Data of food and non-food consumption expenditures as well as household characteristics collected in SBH and SUSENAS has the same concept/definition, but different implementation time. In order to be more efficient in the utilization of resources of the two surveys and to have a better quality of results achieved, in year 2011 a trial of SUSENAS and SBH integration shall be conducted in 7 cities (Medan, Sampit, Denpasar, Kudus, Bulukumba, Tual, and South Jakarta).

Poverty data, CPI/Inflation data, GDP/GRDP are BPS strategic data that have to be released on time. Therefore, planning, field preparation, processing, and presentation of data SUSENAS 2011 activities and trial of integrating SUSENAS and SBH must be in accordance with the set schedule.

Activities of SUSENAS 2011 preparation shall be conducted in year 2010, covering activities of workshop/training of chief instructor with the aim to synchronize the perception toward the concept/definition as well as procedure and protocol of survey implementation. National instructor training will also be conducted in year 2010.

Geographic coverage

National coverage, representative to the district level

Analysis unit

Household Members (Individual) and Household

Universe

Susenas 2011 cover 300,000 household sample spread all over Indonesia where each quarter distribute about 75,000 household sample (including 500 households additional sample for Survey in Maluku Province). The result from each quarter can produce national and provincial level estimates. Meanwhile from the cummulative four quarter, the data can be presented until the district/municipality level.

Sampling procedure

Sampling method is the structured three phase sampling with the following method:

a. First phase, selection of nh census area from Nh with pps (Probability Proportional to Size)with sizeas the total households of SP2010 (M i ).The census area is then randomly allocated into four quarters. Total sampling will be nh= 30,000 census areas thus there will be 7,500 census areas for each quarter. From 7,500 census areas of the First Quarter of the National Socio-Economic Survey (Susenas), some 5,000 census areas are systemically selected for the First Quarter of the 2011 National Labor Force Survey (Sakernas) and will be used again for the second, third and fourth quarter

b. Second phase, to select: - two BS from each selected census area of the second and third quarter of Susenas, and the first quarter which is also selected for the first quarter of Sakernas, which then from the selected census blocks, is randomly allocated one for Susenas/SBH, and one [for] Sakernas, or - one BS from each selected census area of the fourth quarter and first quarter only for Susenas with pps with a household size of SP2010-RBL1.

c. Third phase, from each selected census block for Susenas, a number of regular households are systemically selected (m=10) based on the updated SP2010-C1 household listing by using the VSEN11-P List. Names of household head (KRT) are extracted from SP2010-C1 for name, address and education level variables, followed by field updates.

Mode of data collection

Face-to-face

The dataset contains data on the average monthly expenditure of Milanese households for the consumption of food and non-food items. Within the two aforementioned types, goods are grouped by expense category (eg bread and cereals, meat) and within each category by sub-category (eg meat category - white meat sub-category). Alongside the average monthly expenditure calculated on the whole of households, there are two other items useful for completing the picture: the average calculated with respect to actual purchasers which indicates the average monthly expenditure for each category and sub-category of expenditure, calculated taking into account only the households actually buy the goods in that specific category (for example, not all households buy fish, therefore the average is lower if calculated on all households in the sample, but rises if calculated only on the households that consume it). The other item is the purchase frequency which indicates the percentage of households that consume goods belonging to each specific sub-category. The data refer to the period 2007-2013 and are expressed in euro. The source of the data is the survey "Consu-Mi, Observatory on the consumption of households residing in the Municipality of Milan - 2013 edition" conducted by the Chamber of Commerce in collaboration with the Municipality of Milan. Note: a subsequent edition of the 'investigation.

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Abstract

To facilitate the use of data collected through the high-frequency phone surveys on COVID-19, the Living Standards Measurement Study (LSMS) team has created the harmonized datafiles using two household surveys: 1) the country’ latest face-to-face survey which has become the sample frame for the phone survey, and 2) the country’s high-frequency phone survey on COVID-19.

The LSMS team has extracted and harmonized variables from these surveys, based on the harmonized definitions and ensuring the same variable names. These variables include demography as well as housing, household consumption expenditure, food security, and agriculture. Inevitably, many of the original variables are collected using questions that are asked differently. The harmonized datafiles include the best available variables with harmonized definitions.

Two harmonized datafiles are prepared for each survey. The two datafiles are: 1. HH: This datafile contains household-level variables. The information include basic household characterizes, housing, water and sanitation, asset ownership, consumption expenditure, consumption quintile, food security, livestock ownership. It also contains information on agricultural activities such as crop cultivation, use of organic and inorganic fertilizer, hired labor, use of tractor and crop sales.
2. IND: This datafile contains individual-level variables. It includes basic characteristics of individuals such as age, sex, marital status, disability status, literacy, education and work.

Geographic coverage

National coverage

Analysis unit

• Households
• Individuals

Universe

The survey covered all de jure households excluding prisons, hospitals, military barracks, and school dormitories.

Kind of data

Sample survey data [ssd]

Sampling procedure

See “Nigeria - General Household Survey, Panel 2018-2019, Wave 4” and “Nigeria - COVID-19 National Longitudinal Phone Survey 2020” available in the Microdata Library for details.

Mode of data collection

Computer Assisted Personal Interview [capi]

Cleaning operations

Nigeria General Household Survey, Panel (GHS-Panel) 2018-2019 and Nigeria COVID-19 National Longitudinal Phone Survey (COVID-19 NLPS) 2020 data were harmonized following the harmonization guidelines (see “Harmonized Datafiles and Variables for High-Frequency Phone Surveys on COVID-19” for more details).

The high-frequency phone survey on COVID-19 has multiple rounds of data collection. When variables are extracted from multiple rounds of the survey, the originating round of the survey is noted with “_rX” in the variable name, where X represents the number of the round. For example, a variable with “_r3” presents that the variable was extracted from Round 3 of the high-frequency phone survey. Round 0 refers to the country’s latest face-to-face survey which has become the sample frame for the high-frequency phone surveys on COVID-19. When the variables are without “_rX”, they were extracted from Round 0.

Response rate

See “Nigeria - General Household Survey, Panel 2018-2019, Wave 4” and “Nigeria - COVID-19 National Longitudinal Phone Survey 2020” available in the Microdata Library for details.

Abstract

The Household Income and Expenditure Survey (HIES) was conducted by the Department of Census and Statistics (DCS) under the National Household Survey Programme (NHSP) of Sri Lanka. The survey provides information on household income and consumption expenditure to measure the levels and to observe the changes of living conditions of people in the country. The HIES information is also used to estimate consumption needs of the country and to compute various other important indicators related to poverty and price indices.

Geographic coverage

National coverage

Analysis unit

• Household
• Individual

Kind of data

Sample survey data[ssd]

Frequency of data collection

Every 5 years

Sampling procedure

Sample design of the 2016 HIES was two-stage stratified sampling. Area of residence (Urban and Rural) and the Estate sectors in each district of the country were the selection domains thus the district was the main domain used for the stratification. The sampling frame was the list of housing units prepared for the Census of Population and Housing (CPH) 2011.

• Primary Sampling Units (PSUs) were the census blocks selected at the first stage of the selection.
• Secondary Sampling Units (SSUs) or Final sampling units (FSUs) were the housing units selected at the second stage from the 2,500 PSUs selected at the first stage. From each PSU, 10 SSUs (housing units) were systematically selected giving each housing unit in the PSU an equal probability to be selected for the survey.

Mode of data collection

Face-to-Face[f2f]

Research instrument

The 2016 HIES survey questionnaire consists of nine sections. - Section 1: Demographic Characteristics - Section 2: School Education (For people aged 5 - 20 years) - Section 3: Health - Section 4: Expenditure - Section 5: Income - Section 6: Inventory of Durable Goods - Section 8: Housing Information - Section 9: Agricultural Holdings and Livestock

According to a survey, **** percent of women respondents in China had purchased women's intimate care products more frequently in 2023. At the same time, merely *** percent had reduced their spending frequency.

Purpose and brief description The Harmonised Index of Consumer Prices (HICP) is an economic indicator designed to measure over time the price evolution of goods and services purchased by households. The HICP therefore allows for a comparable measurement of inflation in the euro area, the EU, the European Economic Area and for all other countries including candidate countries for the European Union. The HICP is calculated in a harmonised manner and on the basis of common concepts. The HICP is the official measure of inflation in the euro area to enable the European Central Bank to conduct its monetary policy. Population Final expenditure of households living on Belgian territory. Frequency Monthly. Release calendar Results available 15 days after the reference period Definitions Harmonised consumer price index (HICP): The Harmonised Index of Consumer Prices (HICP) was created in 1997 in order to have a comparable measurement of the inflation among the participating countries of the future euro area. Since the inception of the euro, the HICP has been one of the European Central Bank's (ECB) most important measuring instruments in the conduct of its monetary policy. The collected prices are those actually borne by the consumers, including for example taxes on products, such as value added tax, and take into account the sales periods. Inflation: Inflation is defined as the ratio between the value of the consumer price index of a given month and the index of the same month the year before. Therefore, inflation measures the rhythm of the evolution of the overall price level. COICOP; COICOP is a nomenclature, developed by the United Nations, that aims to classify individual consumption expenditures of households according to purpose. Harmonised Index at constant tax rates: The Harmonised Index of Consumer Prices at constant tax rates is derived from the HICP and is calculated by keeping the level of indirect taxes (mainly excise duties and VAT) constant compared to the level observed in December of the previous year. This index allows measuring the maximum effect on the inflation of changes in taxes by assuming that they are directly and fully passed on to the final price paid by consumers. Weighing: Weight in the basket of goods and services determined by the results of the national accounts (expenditure optics) and those of the household budget survey. Inflation at constant tax rates: Inflation is defined as the ratio between the value of the consumer price index of a given month and the index of the same month the year before. Therefore, inflation measures the rhythm of the evolution of the overall price level. Metadata Harmonised Index of Consumer Prices.pdf Monthly survey of consumer prices by surveyors in stores.pdf 'Private rents' survey.pdf 'Social rents' survey.pdf Other various sources (Internet, catalogues, scanner data, ...).pdf

This statistic shows how often Canadians examined their personal spending habits as of August 2015. The survey results revealed that ** percent of the Canadians aged 35-54 revised their personal spending habits monthly.

Abstract

The project likely increased the incomes of most but not all participants. The spillover effects of change in household income was not as wide as originally anticipated. In general, we found that the program is much more effective for the high performing households. Indeed, the upper quantile, high performing households exhibit a 50% larger impact on their income in targeted activities, and their observed household living standards (as measured by per-capita consumption expenditures) increase significantly 2-3 years after joining the RBD program. In contrast, the lower quantile households show no increase in living standards, even after 3-4 years in the program.

Geographic coverage

The project was delivered in two small districts in northwest Nicaragua: Leon and Chinadega. These two districts cover a rather small geographic coverage.

Analysis unit

Producers: those persons living on the farm who make the decision about farm's production, inputs to production

Universe

The sample list contained information about potential farmer leaders, the location of their farms, the communities where the eligible farmers could be found, and a radius of coverage within which about 30 farmers could be found (using the leader's farm as the origin). The program did not dispose of a complete list of names of potential satellite farmers. In order to get more precise information about the number and location of eligible farmers around the leader, a quasi-census of eligible farmers was carried out, using specific criteria provided by the RBD Program for each type of activity (Table 2). These criteria specified minimum and maximum farm sizes, minimum levels of farmer experience in that target crops, and also stipulated that it must be possible to reach the farm by road during all seasons. Starting at the leader's farm, the quasi-census verified the characteristics of all neighboring farmers until a sampling quota of 30 eligible farmers was reached, or until the maximum radius was reached. Using the quasi-census, 3000 farmers were identified, spread over 140 geographical units (clusters). From every list of clusters, we expected to randomly select 12 farmers.

Kind of data

Sample survey data [ssd]

Sampling procedure

The challenge of this and all impact evaluation efforts is to identify a control group that is identical to the treatment group in every way except that they have not benefitted from the intervention under evaluation.the evaluation team worked with the RBD implementation team to identify all geographic clusters that would eventually be observed RBD services. The evaluation team then selected a subset of these clusters for random assignment to either early or late treatment status. This strategy not only created a temporary conventional control group, it also randomized the duration of time in the program, a feature that will prove vital in the continuous treatment estimates presented below.In late treatment clusters, services were not initiated until approximately 18 months later, in early 2009 at the time of the midline survey. Because clusters were randomly allocated to early and late treatment conditions, we can anticipate that on average the late treatment group should function as a valid control group, identical to the early group in every way except early receipt of RBD services. The economic status of the late group in 2009 should thus be a good predictor of what the status of the early group would have been in the absence of RBD services. Both early and late treatment clusters were then surveyed again near the end of the program in 2011. Once the random assignment of early and late clusters was made, the impact evaluation team created a roster of all eligible producers in these clusters, and then randomly selected a sample of 1600 households split between early and late areas. These 1600 households were then invited to participate in the impact study, and completed a baseline survey in late 2007, just as the RBD project was beginning in the early treatment clusters. Within these clusters, 64% of the eligible households chose to participate in the RBD project. A second-round survey was applied to all 1600 households in the first quarter of 2009, just as the RBD project was rolled out in the late treatment area. While it was not clear at baseline which of the eligible households in the late treatment areas would choose to participate in the project, those households made their participation decision around the time of the second-round survey. Similar to the early treatment clusters, 57% of eligible households in late treatment clusters elected to participate. Because the timing of the surveys and project rollout allow determination of farmer type in both early and late treatment areas (participants versus non-participants), the impact evaluation has the opportunity to study impacts on both eligible households as well as impacts on participating or complier households. The evaluation here will primarily focus on the complier households as we are interested in the impact of the program on the types of self-selecting individuals who adopt it.

Sampling deviation

In some cases, the number of eligible farmers within the permitted radius was insufficient for the creation of a nucleus, and these potential farmers were therefore not included in the original sample. In numerous cases, the quota of 30 farmers was difficult to reach. Combined with the fact that 4% of farmers rejected to be interviewed, and that some 10% were deemed ineligible at the moment of the baseline survey, this all resulted in slightly fewer surveys per cluster than originally planned.

Research instrument

While it was not clear at baseline which of the eligible households in the late treatment areas would choose to participate in the project, those households made their participation decision around the time of the second-round survey. Similar to the early treatment clusters, 57% of eligible households in late treatment clusters elected to participate. Because the timing of the surveys and project rollout allow determination of farmer type in both early and late treatment areas (participants versus non-participants), the impact evaluation has the opportunity to study impacts on both eligible households as well as impacts on participating or complier households. The evaluation here will primarily focus on the complier households as we are interested in the impact of the program on the types of self-selecting individuals who adopt it. From every list of clusters, we expected to randomly select 12 farmers. In practice, there were fewer eligible farmers than we initially assumed. In some cases, the number of eligible farmers within the permitted radius was insufficient for the creation of a nucleus, and these potential farmers were therefore not included in the original sample. In numerous cases, the quota of 30 farmers was difficult to reach. Combined with the fact that 4% of farmers rejected to be interviewed, and that some 10% were deemed ineligible at the moment of the baseline survey, this all resulted in slightly fewer surveys per cluster than originally planned.At the end of this second sampling stage, 1600 farmers (and their households) were interviewed (see Table 6). There are slightly more early (treatment) farmers than late (control) farmers. Within the blocks, there is an uneven number of interviews between early and late groups, especially with the sesame activity.

Cleaning operations

Regarding the variables used to compute the aggregate expenditures, the evaluation team did the following task in the cleaning process:

1) Identification of mistyped data by finding extreme values of per capita durable and non durable aggregate expenditures growth. 2) Revision of every missing value to verify if it was a mistyped data. 3) Consistency between section 3.C, 3.CA and 3.CO to verify if there was information that was not typed.

In most cases, it was identified that the enumerator wrote an incorrect code. However, enumerators were encouraged to write observations if they had some doubt about the farmer’s answer. This type of information was key for the cleaning data process.

In other cases, wrong codes of frequency or total value were evident but there was not additional information from the enumerator (e.g., a household consumes 50 pounds of sugar per day). By comparing this information with the other round survey and considering that the size of household had not changed, we concluded that household consumption was the same amount of food but the frequency or the value was not coherent.

Finally, if there was a household with only one missing value in only one round of the survey, we impute a value for this unique missing value. For example, if the missing value was a food value, we take the average of the value of the same food declared by other households living in the same municipality.

Response rate

At the end of this second sampling stage, 1600 farmers (and their households) were interviewed.There are slightly more early (treatment) farmers than late (control) farmers. Within the blocks, there is an uneven number of interviews between early and late groups, especially with the sesame activity. Some sesame areas contained fewer eligible farmers, resulting in a lower number of interviews per GU. Across departments, the largest differences are found in some bean GUs: Chinandega has twice as many bean GUs as León. This difference is mainly explained because the GUs are spread across four municipalities in Chinandega, and only two municipalities in León.

Abstract

The ultimate objective of the BMTHS is to have a high frequency programme of household surveys that is predictable, flexible and amenable to the ever increasing and changing data needs for government, private sector, planners and researchers. The BMTHS provides a permanent platform for the collection of socio-economic data. This is in contrast to the inter-censal programme of surveys, which is, to a large extent adhoc in nature in that the surveys are infrequent, and the emerging stakeholder needs which have not been planned for are done on adhoc basis.

Specific Survey objectives

It is imperative that a well-coordinated, predictable data provision framework is put in place in the form of BMTHS, as compared to the inter-censal programme of surveys. The BMTHS will provide more frequent, stakeholder specific data that enable policy makers and planners to use real time data in formulation of policies and programmes. The continuous (yearly) nature of the BMTHS allows for close monitoring of programmes, ensuring timely interventions and programme/policy fine tuning. This will lead to robust, responsive relevant programmes that would ultimately improve on the livelihoods of Batswana and the economy. Savings on development budget would be realized due to effective informed policies and programmes.

The BMTHS is set out to;

· provide socio-demographics of the Botswana population; · Provide poverty datum line (PDL) in the country · Provide a list of indicators that monitor poverty
· Provide disaggregated information on poverty levels for monitoring and evaluation of eradication programmes on more regular basis · Continuously provide profiles of poor households. · Profile the poor to assist stakeholders identify the poor among the population · Provide household expenditure information to be used in re-basing of Consumer Price Index · Measures of both current and usual economic activity · Obtain a measure of the size of employment in both formal and informal sectors · Measure of unemployment and underemployment · Determine the size of economically active and inactive population · Provide information on education attainment, occupation and employment status · Determine the impact of education and health among on poor population; · Determine the impact of agriculture among poor population.

Survey Methodology

The Survey methodology outlines the sampling, data collection, processing, publicity and analysis methodologies and strategies employed in the conduct of the BMTHS.

Survey Sampling The Botswana Multi-Topic Household Survey like most national surveys, employed a two stage stratified sampling design. The procedure was made plausible by the existing stratification of twentyseven (27) census districts which are heterogeneous in nature and are aligned to administrative districts. In this structure, the census districts were further grouped into three (3) domains, being; cities/ towns, urban villages and rural areas. The survey only targeted households in all districts and sub-districts. It did not cover institutions such as prisons, army barracks, hospitals and other institutions because the survey was meant to investigate poverty and employment levels at households and individual level.

Geographic coverage

The coverage- nation-wide using administrative district and sub-districts that are usually used by Statistics Botswana in most surveys and censuses

Analysis unit

individuals, households, and communities.

Universe

The survey only targeted households in all districts and sub-districts. It did not cover institutions such as prisons, army barracks, hospitals and other institutions because the survey was meant to investigate poverty and employment levels at households and individual level.

Sampling procedure

The Botswana Multi-Topic Household Survey like most national surveys, employed a two stage stratified sampling design. The procedure was made plausible by the existing stratification of twenty seven (27) census districts which are heterogeneous in nature and are aligned to administrative districts. In this structure, the census districts were further grouped into three (3) domains, being; cities/ towns, urban villages and rural areas. The survey only targeted households in all districts and sub-districts. It did not cover institutions such as prisons, army barracks, hospitals and other institutions because the survey was meant to investigate poverty and employment levels at households and individual level. Botswana Multi-Topic Household Survey Report 2015/16 Statistics Botswana In light of the above, the first stage was the selection of Enumeration Areas (EAs) as Primary Sampling Units (PSUs) with Probability Proportional to Size (PPS) where measure of size is the number of households in an EA as defined in the 2011 Population & Housing Census. This yielded 599 Enumeration Areas.

Mode of data collection

Face-to-face [f2f]

Research instrument

A household questionnaire was administered in each household, which collected various information on household members including sex, age, relationship, and orphan hood status.

Cleaning operations

The data editing should contain information on how the data was treated or controlled for in terms of consistency and coherence. This item does not concern the data entry phase but only the editing of data whether manual or automatic. - Was a hot deck or a cold deck technique used to edit the data? - Were corrections made automatically (by program), or by visual control of the questionnaire? - What software was used?

If materials are available (specifications for data editing, report on data editing, programs used for data editing), they should be listed here and provided as external resources.

Example:

Data editing took place at a number of stages throughout the processing, including: a) Office editing and coding b) During data entry c) Structure checking and completeness d) Secondary editing e) Structural checking of SPSS data files Detailed documentation of the editing of data can be found in the "Data processing guidelines" document provided as an external resource.

Response rate

Response rates for the survey

Variable Estimates Response Response rate
Enumeration Areas (PSU) 599 598 99.8
Households (SSU) 7,188 7,060 98.2
Persons Participation 25,130 24,720 98.4

Sampling error estimates

For sampling surveys, it is good practice to calculate and publish sampling error. This field is used to provide information on these calculations. This includes: - A list of ratios/indicators for which sampling errors were computed. - Details regarding the software used for computing the sampling error, and reference to the programs used (to be provided as external resources) as the program used to perform the calculations. - Reference to the reports or other document where the results can be found (to be provided as external resources).

Example:

Estimates from a sample survey are affected by two types of errors: 1) non-sampling errors and 2) sampling errors. Non-sampling errors are the results of mistakes made in the implementation of data collection and data processing. Numerous efforts were made during implementation of the 2005-2006 MICS to minimize this type of error, however, non-sampling errors are impossible to avoid and difficult to evaluate statistically.