Abstract

The EICV-W4 survey (Enquête Intégrale sur les Conditions de Vie des ménages) was conducted over a 12-month cycle from October 2013 to October 2014. Data collection was divided into 10 cycles in order to represent seasonality in the income and consumption data. A main cross-sectional sample survey, a panel survey and a VUP sample survey were conducted simultaneously.

The EICV-W4 provides information on poverty and living conditions in Rwanda and measures changes over time as part of the on-going monitoring of the Poverty Reduction Strategy and other Government policies. The survey data are also very important for national accounts and updating the consumer price index (CPI).

Geographic coverage

National coverage, including rural and urban households and allowing province- and district-level estimation of key indicators

Analysis unit

Households

Universe

All household members (variable s1q15 identifies household membership).

Kind of data

Sample survey data [ssd]

Sampling procedure

The EICV4 cross sectional (CS) sample includes two independent subsets selected using different sampling frames: 1) a new EICV4 sample of households in enumeration areas (EAs) selected using the 2012 Rwanda Population and Housing Census frame and 2) a panel of households selected from 177 EICV3 villages. A new listing of households was conducted in both the panel and new sample clusters in order to update the frame for the CS Survey. The sample households in the new CS sample EAs were selected from the new listing.

1) The new EICV4 sample The main sampling frame for the EICV4 is based on the 2012 Rwanda Census. The primary sampling units (PSUs) are the 2012 census Enumeration Areas (EAs). In the Census, each EA was classified as urban, semi-urban, peri-urban or rural. The urban areas include Kigali-Ville and the district capitals. The semi-urban areas generally correspond to smaller towns that have service facilities and markets. The peri-urban areas currently have the characteristics of rural areas, but they are located on the periphery of urban areas and are designated for future development. For the EICV4 sampling frame, the semi-urban areas were grouped with the urban strata, and the peri-urban areas with the rural strata. This results in a final distribution of 17.2% urban households and 82.8% rural households in the sampling frame. EAs in the 177 EICV3 sample villages selected for the panel study were excluded from the sampling frame, in order to avoid any overlap between the two samples.

The new EICV4 sample of 12,312 households was selected using a stratified two-stage design. At the first stage, sample EAs were selected within each stratum (district) with probability proportional to size (PPS) from the ordered list of EAs in the sampling frame. The EAs are implicitly stratified by urban and rural strata within each district, ordered first by urban, semi-urban, peri-urban and rural areas, and then geographically by sector, cellule, village and EA codes. This first stage sampling procedure provides a proportional allocation of the sample to the urban and rural areas of each district. At the second stage, households in each sample EA are selected from the listing. For the three districts in Kigali Province, 9 households were selected in each sample EA as original households; for the remaining 27 districts, 12 households were selected in each sample EA as original households. In addition, a reserve sample of 3 replacement households were selected for each sample EA in Kigali Province and 4 replacement households for each sample EA in the remaining provinces.

This new EICV4 sample contains 12,312 households, including 12,233 original households and 79 replacement households.

2) Households from 177 EICV3 villages used for panel study The second component of the EICV4 cross sectional sample consists of all the sample households interviewed inside the 177 EICV3 villages selected for the panel study (including any replacements households and panel split households inside the clusters).

Within each of the 177 villages, all households that were interviewed during EICV3 were included in the cross-sectional sample. When an EICV3 sample household moved and a new household occupied the same house in the cluster, it was interviewed for the Cross-Sectional Survey, and assigned a PID (dependency) code of 94. If an EICV3 household was empty or not found, a random replacement household was selected for the EICV4 Cross-Sectional Survey from the new listing of the sample cluster, and assigned a PID code of 95. The sample households with PID codes 94 and 95 are only used for the cross-sectional study, not the panel study.

This second component of the cross-sectional sample includes 2108 households drawn from the 177 EICV3 villages sampled for the panel study. These include 1604 original EICV3 households, 181 dependent household splitting from the original household in the same cluster, along with 243 households living in the dwelling formerly occupied by a panel household and 80 replacement households in the cluster in order to have 9/12 households per cluster.

The reason why we combine the EICV4 data from the new and panel clusters for the CS analysis is to obtain the most accurate CS estimates. In the case of the CS estimates from the combined samples, the additional data from the 177 sample panel clusters will result in a significant reduction in the variance component of the MSE. Although the bias of the CS data from the sample panel clusters may slightly increase the bias component, this bias is very small compared to the corresponding reduction in the variance component. Therefore the CS results from the EICV4 data for the combined new and panel clusters can be considered more accurate than the corresponding results using only the EICV4 data for the new sample clusters.

In total, the final EICV4 cross-sectional sample contains 14,419 households.

3) Assignment of EAs to cycles and sub-cycles Data collection covering a period of 12 month is divided into 10 cycles to represent seasonality in consumption, income, employment and agricultural activity patterns. For rural enumeration, each cycle is further divided into two sub-cycles. For the 177 EICV3 villages, the cycle and sub-cycle were pre-determined. Households were re-interviewed in the same cycle, corresponding to the same time of the year as they were in EICV3. To assign cycles to the new EICV4 sample EAs, random cycle numbers from 1 to 10 were generated to identify the selection sequence. For the 27 districts outside Kigali, sub-cycle numbers of 1 or 2 were assigned systematically with a random start. This process ensured that the final distribution of the sample EAs to cycles and sub-cycles was geographically representative within each district.

Mode of data collection

Face-to-face paper [f2f]

Research instrument

The same questionnaire was used for cross-sectional, panel and VUP samples. Part A of the questionnaire contains modules on household and individual information. Part B is on agriculture and consumption. The questionnaire was developed in English, and translated into Kinyarwanda.

Questionnaire design took into account the requests raised by major data users and stakeholders, as well as consistency with the previous EICV questionnaires. In addition to methodological improvements, some simplifications were made:

-The major changes introduced in this survey were changes to Section 6, the Economic Activity. Further questioning was added on unemployment and underemployment in response to questions from users, and also to comply with international standards. The section was simplified to enable the analysis to be undertaken by local analysts.

-The Section on the VUP participation was expanded to provide more information, better classification of beneficiaries and to provide greater consistency within the questionnaire. The same questionnaire is to be used on the separate VUP sample which runs in parallel with the EICV4

-The health section was reduced to try to cut respondent burden, as health-related information is being collected by Demographic and Health Surveys (DHS).

-The expenditure section was changed in minor ways to provide better information for national accounts (housing investment) and for CPI weights (retail outlets).

Questionnaire was tested in pilot surveys and amended in time prior to the fieldwork starting in October 2013.

The complete questionnaire is provided as external resources.

Cleaning operations

A day before the interview started, the enumerator, accompanied by a controller, did an introduction to household, explaining how often they will come in that household and delivering a letter indicating that the HH has been selected.

During the field work, after each cycle, the data processing team produced tables and reports of inconsistencies, which were checked by the field supervisor. The data entry system also contained consistency checks that alerted the data entry operators. In case of an alert, the questionnaire was sent back to the supervisor of data entry for correction.

Response rate

Out of the 12,312 sample households selected in the new sample clusters for EICV4, only 79 were non-interviews, for a response rate of 99.4% for this sample. All of the 79 non-interviews were replaced. There were only 12 refusals, and there were few cases of houses that were empty or not found, given that the listing was conducted very close to the interviewing period.

Abstract

The 2010-2011 Integrated Household Living Conditions Survey or EICV III (Enquête Intégrale sur les Conditions de Vie des Ménages) is the third in the series of surveys which started in 2000-2001 and is designed to monitor poverty and living conditions in Rwanda. The survey methodology has changed little over its 10 years, making it ideal for monitoring changes in the country. In 2010-2011, for the first time the achieved sample size of 14,308 households in the EICV III was sufficient to provide estimates which are reliable at the level of the district.

Geographic coverage

National coverage

Analysis unit

For the purposes of this study, the following units of analysis are considered:

-communities -households -persons

Universe

All household members.

Kind of data

Sample survey data [ssd]

Sampling procedure

The EICV III sampled a total of 14,310 households in 1,230 sample villages.The sample selection methodology for EICV III was based on a stratified two-stage sample design.

At the first sampling stage the sample villages for EICV III were selected within each stratum (district) systematically with PPS from the ordered list of villages in the sampling frame. The measure of size for each village was based on the total number of households identified in the sampling frame of villages. The villages within each district were ordered first by urban, mixed and rural areas, and then geographically by secteur, cellule and village codes. This provided implicit geographic stratification of the sampling frame for each district, and ensured a proportional allocation of the sample to the urban and rural areas of each district.

A listing of households was conducted in each sample village prior to the EICV III enumeration in order to select the sample households. A systematic sample of 9 households was selected from the listing for each sample village in Kigali Province and 12 households for each sample rural village in the remaining provinces. A reserve sample of 3 replacement households was selected for each sample village in Kigali Province and 4 replacement households for each sample village in the remaining provinces.

Sampling deviation

Two households were dropped due to incomplete data. These were in the urban zone (Kigali). These include Nyraungenge and Kikukiro. These have been adjusted in the weights.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnarie of the Integrated Household Living Conditions Survey 2010-2011 includes 10 sessions: Information on members of household, Education, Health, Migrations and domestic trips, Housing, Economic activity in last 12 months & last 7 days, Non-agricultural activities , Agriculture, Household expenditure and subsistence farming, Transfers of incomes, other revenues and expenditures, and Credit, durables and savings.

The English and Kinyarwanda questionnaires are both provided as external resources.

Cleaning operations

Extensive cleaning was carried out on the EICV III data. A detailed report on this process is available at the NISR.

Response rate

Traditionally response rates are high in Rwanda so it is not surprising to have response rates greater than 95%. For computing the response rates, the DHS definition is used:

1. The numerator are the number of households with a completed household interview.
2. The denominator: is the sum of number of households with a completed household interview, households that live in the dwelling but no competent respondent was at home, households with permanently postponed or refused interviews, and households for which the dwelling was not found.
3. Unoccupied or abandoned dwelling are excluded (no household lives in the dwelling, address is not a dwelling, or the dwelling is destroyed)

The numerator is: 14,308

To compute the denominator the following are considered:

Completed 14,308
HH not found 132
Sick or die 59
Refused 48
Other 63* Dropped 2

Total: 14,612

The response rate is computed at 98%

*Other is included in the denominator despite the uncertainty of the reason.

**Excluded from the denominator are 368 homes that were reported abandoned or changed.

Dwelling changed (Nyakatasi) 115
Dwelling changed other reason 253

Sampling error estimates

Sampling errors for key indicators are provided in the Annexes of the EICV III reports (main indicators report and thematic reports).

Abstract

The EICV-W5 survey (Enquête Intégrale sur les Conditions de Vie des ménages) was conducted over a 12-month cycle from October 2016 to October 2017. Data collection was divided into 10 cycles in order to represent seasonality in the income and consumption data. A main cross-sectional sample survey, a panel survey and a VUP panel survey were conducted simultaneously.

The main objective of the EICV5 VUP Panel Survey is to provide longitudinal data for a nationally-representative panel of households that received VUP benefits at the time of the EICV4, in order to obtain reliable estimates of trends in the socioeconomic indicators for these households.

Geographic coverage

National coverage.

Analysis unit

Households

Universe

All household members.

Kind of data

Sample survey data [ssd]

Sampling procedure

Sampling frame and sample size of EICV5 VUP panel survey:

The VUP Survey conducted with EICV4 was based on a sample of 2,460 households selected from the VUP administrative frame using a stratified two-stage sample design. The VUP sampling frame was stratified by province and predominant type of VUP beneficiaries (Direct Support, Financial Services and Public Works). In the EICV4 VUP Survey it was found that of the original sample of 2,460 VUP households, only 1,520 households indicated that they were receiving VUP benefits at the time of the survey. These 1,520 households are considered the initial baseline panel of VUP households that are being enumerated in the EICV5 VUP Panel Survey. Following a further review of the EICV4 VUP data it was found that 27 of these households did not actually receive any VUP benefits during the reference period, so they were dropped from the EICV5 VUP Panel data set for the analysis, and they will not be assigned any weights. Therefore the final number of eligible EICV4 sample VUP households that was matched to the EICV5 panel households was 1,493.

Mode of data collection

Face-to-face paper [f2f]

Research instrument

The same questionnaire was used for cross-sectional, panel and VUP samples. Part A of the questionnaire contains modules on household and individual information. Part B is on agriculture and consumption. The questionnaire was developed in English, and translated into Kinyarwanda.

Questionnaire design took into account the requests raised by major data users and stakeholders, as well as, consistency with the previous EICV questionnaires. In addition to methodological improvements, some simplifications were made:

-The major changes introduced in this survey were changes to Section 6, the Economic Activity. Further questioning was added on unemployment and underemployment in response to questions from users, and also to comply with international standards. The section was simplified to enable the analysis to be undertaken by local analysts.

-The Section on the VUP participation was expanded to provide more information, better classification of beneficiaries and to provide greater consistency within the questionnaire. The same questionnaire is to be used on the separate VUP sample which runs in parallel with the EICV5

Questionnaire was tested in pilot surveys and amended in time prior to the fieldwork starting in October 2016. The complete questionnaire is provided as external resources.

Cleaning operations

A day before the interview started, the enumerator, accompanied by a controller, did an introduction to household, explaining how often they will come in that household and delivering a letter indicating that the HH has been selected.

During the field work, after each cycle, the data processing team produced tables and reports of inconsistencies, which were checked by the field supervisor. The data entry system also contained consistency checks that alerted the data entry operators. In case of an alert, the questionnaire was sent back to the supervisor of data entry for correction.

Response rate

Following the EICV5 data collection it was found that 175 of these households could not be interviewed because of a death or relocation outside the country. Therefore the final number of eligible EICV5 VUP panel sample households was 1,642, including 324 households from split.

Abstract

Rwanda has experienced fast socio, demographic and economic transformation since the year 2000. It recorded on average 8 percent GDP annual growth since then, mainly driven by agriculture and services. In addition socio-demographic indicators have witnessed substantial improvement from 2000 onward. Following the crisis period; the 1994 genocide against the Tutsi era, the country developed a long term vision “Vision 2020” with five year development programs: PRSP, EDPRS1 and EDPRS2, the main objective of each of the programs was poverty reduction. The need to adequately plan interventions and monitor progress in poverty reduction, estimation of absolute monetary poverty in Rwanda started in a regular manner since 2001 when the first Household Living Condition Survey (Enquête Intégrale sur les Conditions de Vie des Ménages- EICV1) was carried out. EICV 2013-14 provided an update on the level of poverty based on 2013-14 Integrated Household Living Conditions Survey (EICV4) focusing on poverty as measured in consumption terms. The survey also highlighted other trend dimensions of living conditions captured in other surveys that complemented and provided a holistic understanding of poverty and living conditions.

The results of the 2013-14 EICV indicated substantial progress in poverty reduction and improvement in other socio-economic and demographic indicators in the last three years. The survey shows that poverty went down from 44.9 percent in 2011 to 39.1 percent in 2014 and extreme poverty from 24.1 percent to 16.3 percent. This follows similar reduction between 2006 and 2011 where poverty dropped from 56.7 percent to 44.9 percent and extreme poverty decreased from 35.8 percent to 24.1 percent. Inequality reduced with both the Gini coefficient dropping from 0.49 in 2011 to 0.45 in 2014. The ratio of the wealthiest 10 percent to the poorest 10 percent dropped from 6.36 to 6.01 during the same period.

Generally the progress was impressive, however challenges have remained. Many Rwandans are still poor and for many others living conditions still needed to be improved especially in areas of education and employment. The frequency of Integrated Household Living Conditions Survey is every three years, the survey was conducted by the National Institute of Statistics of Rwanda (NISR) in collaboration with different stakeholders in the country over a period of 12 months between October 2013 and October 2014.

Geographic coverage

National

Analysis unit

• Households
• Individuals
• Communities

Kind of data

Sample survey data [ssd]

Sampling procedure

Rwanda used a basic needs approach to measure poverty. In this survey households were classified as poor or non-poor based on consumption per adult equivalent compared with a total poverty line of 159,375 RWF or an extreme poverty line of 105,064 RWF in January 2014 prices. The essential idea was to determine how much it would cost to buy enough food to provide an adequate amount of calories, and then to add a provision for non-food essentials such as shelter and clothing for an adult.

A sub-sample of 1,920 households interviewed in EICV3 (2010-11) was selected to be revisited in EICV4 (2013-14) to allow for a more complete analysis of movements into and out of poverty overtime. The sample was designed to provide representative results at the national and urban/rural levels. The sampling frame for the panel was the list of 1,431 villages visited in EICV3. Households that relocated or split were tracked in order to obtain current information for the corresponding household members. A total of 2,423 households that were visited in 2010-11 were revisited in 2013-14 of which 1,898 were original households and 525 were households that split off from the original households. The same survey questionnaire was administered to both non-panel and panel households, so they were considered to be an integral part of both the EICV3 and EICV4 samples.

The EICV3 and EICV4 samples were each drawn from the 2002 and 2012 census frames respectively, and the sampling was stratified by district. Suitable weights were calculated within the panel samples, and as needed were used for adjustment to reflect the national population. The sample selection procedures were done efficiently taking into consideration the replacement of panel households. Since the EICV3 and EICV4 samples were drawn from different frames, the effect of using different sampling frames and strategies is unclear both for the panel and cross section analysis. One response was to investigate whether the panel is representative of the larger cross-section of households. This was done by testing the hypothesis of equality of sub-sample (i.e. panel) means to the means for the rest of the full sample, for key indicators. The three indicators selected were adult equivalents, household size, and consumption per adult equivalent. Households were divided into two mutually exclusive subsamples: selected panel households, and non-selected households.

Mode of data collection

Face-to-face [f2f]

Research instrument

The survey was comprised of the following questionnaires: 1. Agriculture questionnaire 2. Non-agricultural activities questionnaire 3. Credit, durables and savings questionnaire 4. Education questionnaire 5. Employment questionnaire 6. Household roster questionnaire 7. Health questionnaire 8. Housing and infrastructure questionnaire 9. Migration questionnaire 10. Transfers and income sources questionnaire 11. Household expenditures questionnaire

Abstract

The 2005 Integrated Household Living Conditions Survey, or Enquête Intégrale sur les Conditions de Vie des Ménages (EICV-II) in French, is the second in the series of surveys designed to monitor poverty and living conditions in Rwanda. The objectives of the study are to provide information on poverty and living conditions in Rwanda and to monitor changes over time as part of the ongoing monitoring of the Poverty Reduction Strategy and other Government policies. The results of EICV-II will be compared with the results of EICV-I in 2001 and the content of the questionnaire will be broadly similar to that of the previous survey. In addition the survey will provide data on household income and expenditures which can be used for updating the weights and market basket for the Consumer Price Index (CPI) and components of the national accounts. Survey data on agricultural activities have also proved to be important for national accounts and will complement information provided by future agricultural and rural sector surveys.

The geographic domains of analysis for EICV-II will be Kigali-Ville, other urban and rural strata at the national level, as well as each of the 11 provinces. Given that Rwanda is predominantly rural, the rural stratum of each province will also be a domain of analysis. In order to provide survey results that are comparable to those of EICV-I, the sample design and survey methodology for EICV-I will be consistent with those for the previous survey.

Geographic coverage

National

Analysis unit

• Households
• Individuals
• Communities

Universe

The universe for EICV 2005 includes the households and population living in individual households within all urban and rural areas of Rwanda. The population living in institutions and group quarters such as hospitals, military bases and prisons, are excluded from the sampling frame.

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling frame for the EICV-I was based on the data and cartographic materials from the 1991 Rwanda Census of Population and Housing, while the EICV-II was based on the 2002 Rwanda Census frame. There were significant changes in the areas considered urban between the two censuses, but these geographic changes are taken into account in the comparative analysis between the EICV-II and EICV-II data.

A stratified two-stage sample design was used for both the EICV-I and EICV-II. The primary sampling units (PSUs) were the enumeration areas or zones de dénombrement (ZDs) defined for the census. The sample of ZDs in each stratum was selected with probability proportional to size, where the measure of size was based on the number of households from the census frame. A new listing of households was conducted in each ZD, and a sample of households was selected at the second sampling stage.

Note: Detailed description of sample design is found in the technical document "Rwanda 2005 ECIV-II sampling and weighting".

Sampling deviation

Household that was not interviewed as per the original listing and selection was replaced with a reserve household. Each EA had 4 households on reserve. A total of 522 households were replaced over the course of the survey. In addition, several EAs were swapped from their scheduled cyclic visit due to seasonal accessability problems.

Mode of data collection

Face-to-face [f2f]

Cleaning operations

Detailed data entry, cleaning and data processing information is available in "EICV2 Final Data Processing Report" report.

Response rate

Out of the 6900 household sample, 92.4% responded. All 7.6% of households that were not interviewed were replaced.

Abstract

Since the 1994 Genocide and the total collapse of Rwanda's economy and social services, the country has embarked on rebuilding itself and improving the quality of life of its population. Agricultural production has been continuously increasing and the country is reporting to have produced enough food to feed its entire people since 2008. Health indicators have improved, as has school enrolment, parity between girls and boys in school and access to clean water.

Against this context of socio-economic progress mitigated by population growth, widespread poverty and high levels of chronic malnutrition and food insecurity, it was decided to undertake the third national Comprehensive Food Security and Vulnerability Analysis and Nutrition Survey (CFSVA and Nutrition Survey 2012) in Rwanda. Like previous CFSVAs, the overall objective is to analyze trends of food insecurity, malnutrition and vulnerability over time, measuring the extent and depth of food insecurity and identifying the underlying causes. In addition, building on the recently released EICV 3 and 2010 DHS surveys, this study looks into social protection issues, food insecurity and malnutrition in Rwanda to formulate recommendations so that interventions to tackle poverty, food insecurity and malnutrition can be adequately targeted and designed (including district plans to eliminate malnutrition) and to help monitor progress in the implementation of the Joint Action Plan to fight malnutrition in Rwanda.

Geographic coverage

National coverage

Analysis unit

• Household
• Community
• Anthropometric

Universe

Survey was administered to sample household heads, which also included an anthropometric section for women of reproductive age (15-49), children under five years, and a section on infant and young child feeding practices intended only for children between six months and two years.

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling frame was based on the data from the recent EICV 3 (2010/2011) and was organized according to 30 districts. A two-stage cluster sample procedure was applied. In the first stage, 25 villages per district were randomly selected with probability proportional to population size. In the second stage, 10 households in each of the 25 villages in the 30 districts were selected for participation in the survey. A systematic random sampling technique was chosen for this stage. In total 748 key informant interviews were conducted, 7498 households were administered the household questionnaire, and valid anthropometric measurements were taken for 7418 women and 4651 children. The Infant and Young Child Feeding (IYCF) module was submitted to mothers or caretakers of all children between six and 24 months (1613 children in total).

Mode of data collection

Face-to-face [f2f]

Research instrument

Two instruments were used to collect primary data: a key informant questionnaire and a household questionnaire including an anthropometric section for women of reproductive age, and a section on infant and young child feeding practices intended only for children between six months and two years.

• HOUSEHOLD: Demographics, Housing and Facilities, Livelihoods, Household Assets and Productive Assets, Agricultural Production, Migration & Remittances, Sources of Credit, Expenditures, Food Sources and Consumption, Coping Strategies, Shocks and Food Security External Assistance/Programme participation.

• WOMEN and CHILD: Maternal Health and nutrition, Child Health, Nutrition and feeding practices.

• VILLAGE: Group composition, Demographic and Community Information, Community Infrastructure, Markets (prices of food, animals, daily labour wages), Crop calendar, Assistance projects, Shocks.

The instruments were first developed in English and subsequently translated into Kinyarwanda.

Response rate

99.99%

Abstract

The Household Living Conditions Survey, also known as Enquête Intégrale sur les Conditions de Vie des Ménages (EICV) in French, was conducted by the Statistics Department of the Ministry of Finance and Economic Planning. The survey was primarily intended to provide policy planners and decision-makers with basic data on household living standards in Rwanda.

In addition, the survey was to be used to: - calculate weights for the Consumer Price Index and estimate final household consumption, - measure the effect of macro-economic policies and projects on the conditions and living standards of the population, - produce key indicators of household welfare in order to assist policy-makers and development partners to improve the design of their development strategy, - identify policy target groups with a view to ensuring that state interventions are better targeted. - provide information on the socio-economic characteristics of households with a view to setting up a socio-economic data base. - carry out in-depth studies, for example on poverty, nutrition, housing conditions, etc, - improve the national capability to conduct statistical surveys, however complex they may be.

Geographic coverage

National coverage with all 11 former provinces (now 5 major provinces) and the City of Kigali.

Analysis unit

-Household -Individual -Commodity (for GDP computation)

Universe

Household members (institutional and itinerant populations excluded)

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling plan was drawn up with the technical support of the late Christopher Scott, Survey Consultant, during his mission in July 1997.

Constraints

The two main factors considered in designing the sampling plan were: - the objectives of the survey, - the fieldwork methodology given the available logistical resources. For the survey one objective was determinant: the Government wanted statistically reliable results at the level of each province, Kigali city and the "other urban sector". Thus, the objective called for 13 domain of analysis. Experience of conducting this type of survey shows that a minimum sample of 500 households per domain of study is required for sound analyses.

Sample size

The sample size was therefore 6,450 households, with 1,170 households for urban areas and 5,280 households for rural areas. Two stage sampling A two stage stratified sample was used: sampling at area level and at household level.

Sampling base

*At the area level, the chosen sampling base ( or at the enumeration district) was the "cellule"in the rural areas and the zone in urban areas, since they are usually fairly homogeneous in size and are well demarcated.

Knowledge of the size of each cellule enabled the use of the classical method of sampling with probability proportional to size at the first stage. A list of all cellules including estimates of the number of households in each was compiled from information provided by the local authorities.

*For sampling at the household level, an up-dated list of households was prepared for each of the selected first stage cellule by carrying out a listing in each sampled cellule simultaneously but with a lag in data collection before or while collecting the data. Part of this operation was carried out in collaboration with the National Population Office (ONAPO) and the Food Security Research Project (FSRP) of MINAGRI.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaires are published in French.

Three types of questionnaire were used in the field for data collection: - the household questionnaire comprising of 12 modules divided in two parts, A and B. - the community questionnaire for collecting data on economic and social infrastructures in the sample units in rural areas and - a conversion form for non-standard units used by households.

Household questionnaires

Part A collects data on each member of the household. It covered the following areas: - demographic and migration characteristics, - education and health, - employment and housing.

Part B deals with the economic activity of the household. It comprises of the following five modules: - agro-pastoral activities and own-produce consumption, - household expenditure, - non-agricultural economic activities, - transfers, - durable goods, access to credit and savings.

Cleaning operations

Data Editing (see external resource entilted: Final Data Processing Report)

Questionnaires were reviewd by the controller in the field before they were dispatched for data entry. A control sheet was provided to the contollers to assist in the process of manually editing the questionnaires. Questionnaire structures were verified when the questionnaires were checked in prior to data entry. Three contracted persons reviewed the questionnaire and filled in a form that served as a primary data control sheet. Automated data editing was largely done during the data entry phase (see "Other Data Processing" for details). Some batch edit programs were used to identify inconsistent data.

Data Imputation

Data iimputation was largely done during the analysis phase by analysts. However, a "structural" imputation on the microdata was required for the own consumption data. This was done to adjust for erroneous pricing when the unit for measuring own consumption was buckets. For more information, please refer to the SPSS su=yntax files orthe data processing report.

Primary Data Issues

Coding of products was based on sequential codes for each section.

Response rate

In the course of the survey, some households did not respond, for one reason or the other. Of 6,450 households 6,431 responded, giving a response rate of 99.7%. In the course of processing the data, an additional 11 questionnaires were rejected because they did not contain useable information, in particular in respect to expenditure and consumption. Hence, the analysis was based on 6,420 households, giving a coverage rate of 99.5% of the sample households.

Sampling error estimates

Given that the survey estimates are subject to sampling variability, it is important to calculate the sampling errors for the most important estimates from each survey. The sampling error is measured by the standard error, or square root of the variance of the estimate. The CENVAR software, a component of the Integrated Microcomputer Processing System (IMPS) developed by the U.S. Census Bureau, was used for tabulating the standard errors and other measures of precision, taking into account the stratification and clustering in the sample design. The CENVAR output tables show the value of the estimates, standard errors, coefficients of variation, 95 percent confidence intervals, design effects and number of observations. Given that the confidence intervals provide a user-friendly interpretation of the sampling variability, an annex was produced with tables showing the 95 percent confidence intervals for the most important estimates from the EICV1 and EICV2 data appearing in the preliminary report. These tables provide a quick conservative test to determine whether any difference between the EICV1 and EICV2 estimates is statistically significant.

The INSR was also provided with tables showing the full CENVAR results. The design effect is defined as the variance of an estimate based on the actual sample design divided by the corresponding variance based on a simple random sample of the same size; it is a measure of the relative efficiency of the sample design. In comparing the CENVAR results from EICV1 and EICV2, it was found that the design effects are generally lower for EICV2, indicating that the stratification used for this survey was very effective. Given that the EICV1 was based on an older sampling frame from the 1991 Rwanda Census, this also contributed to the higher design effects for the EICV1 estimates.