Abstract

The UNPS aims at producing annual estimates in key policy areas; and providing a platform for experimenting with and assessing national policies and programs. Explicitly, the objectives of the UNPS include: 1. To provide information required for monitoring the National Development Strategy, of major programs such as National Agricultural Advisory Services (NAADS) and General Budget Support, and also to provide information for the compilation of the National Accounts (e.g. agricultural production); 2. To provide high quality nationally representative information on income dynamics at the household level as well as information on service delivery and consumption expenditure estimates annually; to monitor poverty and service outcomes in interim years of other national survey efforts, such as the Uganda National Household Survey (UNHS), Uganda Demographic and Health Survey (UDHS) and National Service Delivery Surveys (NSDS); 3. To provide a framework for low-cost experimentation with different policy interventions to e.g. reduce teacher absenteeism, improve ante-natal and post-natal care, and assess the effect of subsidies on agricultural inputs among others; 4. To provide a framework for policy oriented analysis and capacity building substantiated with the UGDR and support to other research which feed into the Annual Policy Implementation Review; and 5. To facilitate randomized impact evaluations of interventions whose effects cannot currently be readily assessed through the existing system of national household surveys.

Analysis unit

The study describes (including but not limited to): - Household - Individual - Parcel - Plot - Community

Kind of data

Sample survey data [ssd]

Sampling procedure

The UNPS is carried out over a twelve-month period (a “wave”) on a nationally representative sample of households, for the purpose of accommodating the seasonality associated with the composition of and expenditures on consumption. The survey is conducted in two visits in order to better capture agricultural outcomes associated with the two cropping seasons of the country. The UNPS therefore interviews each household twice in a year, in visits approximately six months apart. In 2009/10, the UNPS set out to track and interview 3,123 households that were distributed over 322 Enumeration Areas (EAs), selected out of 783 EAs that had been visited during the Uganda National Household Survey (UNHS) in 2005/06. The distribution of the EAs covered by the 2009/10 UNPS was such that it included all 34 EAs in Kampala District, and 72 EAs (58 rural and 14 urban) in each of the other regions i.e. Central excluding Kampala, Eastern, Western and Northern which make up the strata. Within each stratum, the EAs were selected with equal probability with implicit stratification by urban/rural and district (in this order). However, the probabilities of selection for the rural portions of ten districts that had been oversampled by the UNHS 2005/06 were adjusted accordingly. Since most IDP (Internally Displaced People) camps in the Northern region are currently unoccupied, the EAs that constituted IDP camps were not part of the UNPS sample. This allocation allows for reliable estimates at the national, rural-urban and regional levels i.e. at level of strata representativeness which includes: (i) Kampala City, (ii) Other Urban Areas, (iii) Central Rural, (iv) Eastern Rural, (v) Western Rural, and (vi) Northern Rural. In the UNPS 2010/11, the concept of Clusters instead of EAs was introduced. A cluster represents a group of households that are within a particular geographical area up to parish level. This was done due to split-off households that fell outside the selected EAs but could still be reached and interviewed if they still resided within the same parish as the selected EA. Consequently, in each subsequent survey wave, a subset of individuals was selected for tracking. The UNPS is part of the long term Census and Household Survey Program hence questionnaires and the timing of data collection are coordinated with the current surveys and census implemented by UBOS. SAMPLE REFRESH Starting with the UNPS 2013/14 (Wave 4) fieldwork, one third of the initial UNPS sample was refreshed with the intention to balance the advantages and shortcomings of panel surveys. Each new household will be visited for three consecutive waves, while baseline households will have a longer history of five or six years, given the start time of the sample refresh. This same sample was used for the UNPS 2015/16 (Wave 5) Once a steady state is reached, each household will be visited for three consecutive years, and at any given time one third of the households will be new, one third will be visited for the second time, and one third for the third (and last) time. The total sample will never be too different from a representative cross-section of the country, yet two-thirds of it will be a panel with a background of a year or two. New households were identified using the updated sample frames developed by the UBOS in 2013 as part of the preparations for the 2014 Uganda Population and Housing Census.

Mode of data collection

Computer Assisted Personal Interview [capi]

Research instrument

The UNPS had six questionnaires namely: Household Questionnaire; Woman Questionnaire; Agriculture & Livestock Questionnaire; Fisheries Questionnaire; Community Questionnaire and Market Questionnaire. A module on Biological data collection was also administered in 2019/20. Each of these questionnaires is divided into a number of sections and the number of questions in each section varies accordingly. It should be noted that in 2013/14, 2015/16, 2018/19, and 2019/20, all questionnaires were administered using the CAPI software .

Abstract

The UNPS aims at producing annual estimates in key policy areas; and providing a platform for experimenting with and assessing national policies and programs. Explicitly, the objectives of the UNPS include:

1. To provide information required for monitoring the National Development Strategy, of major programs such as National Agricultural Advisory Services (NAADS) and General Budget Support, and also to provide information for the compilation of the National Accounts (e.g. agricultural production);

2. To provide high quality nationally representative information on income dynamics at the household level as well as information on service delivery and consumption expenditure estimates annually; to monitor poverty and service outcomes in interim years of other national survey efforts, such as the Uganda National Household Survey (UNHS), Uganda Demographic and Health Survey (UDHS) and National Service Delivery Surveys (NSDS);

3. To provide a framework for low-cost experimentation with different policy interventions to e.g. reduce teacher absenteeism, improve ante-natal and post-natal care, and assess the effect of subsidies on agricultural inputs among others;

4. To provide a framework for policy oriented analysis and capacity building substantiated with the UGDR and support to other research which feed into the Annual Policy Implementation Review; and

5. To facilitate randomized impact evaluations of interventions whose effects cannot currently be readily assessed through the existing system of national household surveys.

Geographic coverage

National

Analysis unit

The study describes (including but not limited to):

• Household

• Individual

• Parcel

• Plot

• Community

Kind of data

Sample survey data [ssd]

Sampling procedure

The UNPS is carried out over a twelve-month period (a “wave”) on a nationally representative sample of households, for the purpose of accommodating the seasonality associated with the composition of and expenditures on consumption. The survey is conducted in two visits in order to better capture agricultural outcomes associated with the two cropping seasons of the country. The UNPS therefore interviews each household twice in a year, in visits approximately six months apart.

In 2009/10, the UNPS set out to track and interview 3,123 households that were distributed over 322 Enumeration Areas (EAs), selected out of 783 EAs that had been visited during the Uganda National Household Survey (UNHS) in 2005/06. The distribution of the EAs covered by the 2009/10 UNPS was such that it included all 34 EAs in Kampala District, and 72 EAs (58 rural and 14 urban) in each of the other regions i.e. Central excluding Kampala, Eastern, Western and Northern which make up the strata.

Within each stratum, the EAs were selected with equal probability with implicit stratification by urban/rural and district (in this order). However, the probabilities of selection for the rural portions of ten districts that had been oversampled by the UNHS 2005/06 were adjusted accordingly. Since most IDP (Internally Displaced People) camps in the Northern region are currently unoccupied, the EAs that constituted IDP camps were not part of the UNPS sample. This allocation allows for reliable estimates at the national, rural-urban and regional levels i.e. at level of strata representativeness which includes: (i) Kampala City, (ii) Other Urban Areas, (iii) Central Rural, (iv) Eastern Rural, (v) Western Rural, and (vi) Northern Rural.

In the UNPS 2010/11, the concept of Clusters instead of EAs was introduced. A cluster represents a group of households that are within a particular geographical area up to parish level. This was done due to split-off households that fell outside the selected EAs but could still be reached and interviewed if they still resided within the same parish as the selected EA. Consequently, in each subsequent survey wave, a subset of individuals was selected for tracking.

The UNPS is part of the long term Census and Household Survey Program hence questionnaires and the timing of data collection are coordinated with the current surveys and census implemented by UBOS.

SAMPLE REFRESH

Starting with the UNPS 2013/14 (Wave 4) fieldwork, one third of the initial UNPS sample was refreshed with the intention to balance the advantages and shortcomings of panel surveys. Each new household will be visited for three consecutive waves, while baseline households will have a longer history of five or six years, given the start time of the sample refresh. This same sample was used for the UNPS 2015/16 (Wave 5)

Once a steady state is reached, each household will be visited for three consecutive years, and at any given time one third of the households will be new, one third will be visited for the second time, and one third for the third (and last) time. The total sample will never be too different from a representative cross-section of the country, yet two-thirds of it will be a panel with a background of a year or two.

New households were identified using the updated sample frames developed by the UBOS in 2013 as part of the preparations for the 2014 Uganda Population and Housing Census.

Mode of data collection

Computer Assisted Personal Interview [capi]

Research instrument

The UNPS had six questionnaires namely: Household Questionnaire; Woman Questionnaire; Agriculture & Livestock Questionnaire; Fisheries Questionnaire; Community Questionnaire and Market Questionnaire. Each of these questionnaires is divided into a number of sections and the number of questions in each section varies accordingly.

It should be noted that in 2013/14, 2015/16 and 2018/19, all questionnaires were administered using the CAPI software except the Fisheries and Market Questionnaires which were not administered.

Geographic coverage

National coverage

Analysis unit

households/individuals

Kind of data

survey

Frequency of data collection

Yearly

Sampling procedure

Sample size:

Abstract

The Uganda National Panel Survey (UNPS) was carried out to collect high quality data on key outcome indicators such as poverty, service delivery, employment and to monitor government's development programs like the National Development Plan (NDP) on an annual basis. The 2010/11 survey collected information on socio-economic characteristics at household, individual and community levels.The UNPS 2010/11 was comprised of six modules: the Socio-Economic, Woman, Agriculture, Fisheries, Community and Market Price modules. The survey covered 3,200 households that were scientifically selected and followed for re-interview in 2009/10 and 2010/11.

The objectives of the survey were: 1) To provide information required for monitoring the NDP and other development objectives like the JAF, MDGs as well as specific programs such as the National Agricultural Advisory Services (NAADS) among others. 2) To provide high quality nationally representative information on income dynamics at the household level as well as annual consumption expenditure estimates to monitor poverty in years between Uganda National Household Surveys (UNHS). 3) To supply regular data on agriculture in order to characterize and monitor the performance of the agricultural sector.

Geographic coverage

National coverage

Analysis unit

• Household
• Individual
• Communities

Kind of data

Sample survey data [ssd]

Sampling procedure

The 2010/11 UNPS survey maintained the 2009/10 UNPS sample design where all the households that were sampled for Wave I (2009/10) were tracked and re-interviewed in Wave II (2010/11).

Out of the 7,400 households interviewed during the UNHS 2005/06, 3,200 households were selected for the UNPS and the same sample was maintained in both 2009/10 and 2010/11 Panel surveys. During data collection, the population of persons interviewed in Wave II was slightly higher than that of Wave I due to the following reasons:

1. About 20 households that had initially been missed in Wave I were found and successfully interviewed in Wave II.
2. Changes in household composition contributed to the increase in the number of persons that were added to the panel. Most importantly, if a household member split-off from his/her original household (e.g. children leaving home to set up their own household,or a couple separates), all the new households were included/ joined the panel. Inclusion of split-offs was the main way in which panel surveys, maintain sample representativeness over the years. The new households formed are known as Split-off households while the individuals are termed as Movers.

Mode of data collection

Face-to-face [f2f]

Research instrument

To suit its multiple objectives, the UNPS was comprised of a set of survey instruments. These were the following questionnaires: 1. Agriculture Questionnaire (administered to the subset of UNPS households engaged in agricultural activities) 2. Household Questionnaire 3. Community Questionnaire

Response rate

84%

Abstract

Uganda has experienced strong economic growth over the past two decades and has made great strides towards improving the quality of life and access to services. In order to continue to promote pro-poor economic growth, the Government of Uganda (GoU) developed the National Development Plan (NDP) and a Joint Budget Support strategy as part of the implementation of the National Development Strategy (NDS).

Uganda recognizes the need for adequate data collection to effectively monitor outcomes of the National Development Strategy (NDS). For this purpose, the Uganda Bureau of Statistics (UBOS) implemented the Uganda National Panel Survey (UNPS) program, with financial and technical support from the Government of Netherlands, and the World Bank Living Standards Measurement Study - Integrated Surveys on Agriculture (LSMS-ISA) project.

The 2005-2009/10 Uganda National Panel Survey (UNPS) is the first "panel" survey done by the LSMS group. The households included were chosen from the 2005-06 Uganda National Household Survey (UNHS).
The sample One of the primary uses of the UNPS is to inform policymaking in advance of the Budget, through descriptive reports that are made ready in time for the initial work on sector budget framework papers.

Survey Objectives The UNPS aimed at producing annual estimates of outcomes and output in the key policy areas and at providing a platform for the experimentation and assessment of national policies and programs.

Explicitly, the objectives of the UNPS include: The UNPS aims at producing annual estimates in key policy areas and at providing a platform for experimenting with and assessing of national policies and programs. Explicitly, the objectives of the UNPS include: 1. To provide information required for monitoring the National Development Strategy, of major programs such as National Agricultural Advisory Services (NAADS) and General Budget Support, and also to provide information to the compilation of the National Accounts (e.g. agricultural production). 2. To provide high quality nationally representative information on income dynamics at the household level and provide annual information on service delivery and consumption expenditure estimates to monitor poverty and service outcomes in interim years of other national survey efforts, such as the Uganda National Household Survey (UNHS), Uganda Demographic and Health Survey (UDHS) and National Service Delivery Surveys (NSDS). 3. To provide a framework for low-cost experimentation with different policy interventions to e.g. reduce teacher absenteeism, improve ante- and post-natal care, or assessing the effect of agricultural input subsidies. 4. To provide a framework for policy-oriented analysis and capacity building substantiated with the UGDR and support to other research which will feed into the Annual Policy Implementation Review. 5. To facilitate randomized impact evaluations of interventions whose effects cannot currently be readily assessed through the existing system of national household surveys.

Geographic coverage

National

Analysis unit

• Households
• Individuals
• Markets
• Communities / facilities

Kind of data

Sample survey data [ssd]

Sampling procedure

Survey Design The UNPS is carried out annually, over a twelve-month period on a nationally representative sample of households, for the purpose of accommodating the seasonality associated with the composition of and expenditures on consumption. The survey is conducted in two visits in order to better capture agricultural outcomes associated with the two cropping seasons of the country. The UNPS will therefore interview each household twice each year, in visits six months apart.

Starting in 2005-09/10, the UNPS has been set out to track and re-interview 3,123 households that were distributed over 322 enumeration areas (EAs), selected out of the 783 EAs that had been visited by the Uganda National Household Survey (UNHS) in 2005-06. The UNPS EAs covered all 34 EAs visited by the UNHS 2005-06 in Kampala District, and 72 EAs (58 rural and 14 urban) in each of the (i) Central Region with the exception of Kampala District, (ii) Eastern Region, (iii) Western Region, and (iv) Northern Region.

Within each stratum, the UNPS EAs were selected from the UNHS 2005-06 EAs with equal probability, and with implicit stratification by urban/rural and district (in this order), except for the rural portions of the ten districts that were oversampled by the UNHS 2005-06. In these districts, the probabilities were deflated, to bring them back to the levels originally intended. Since IDP camps are now mostly unoccupied, the extra EAs in IDP camps are not a part of the UNPS subsample. This allocation strives for reasonably reliable estimates for the rural portion of each region, and for the set of urban areas out of Kampala as a whole, as well as the best possible estimates for Kampala that can be expected from a subsample of the UNHS 2005-06. Therefore, the UNPS strata of representativeness include (i) Kampala City, (ii) Other Urban Areas, (iii) Central Rural, (iv) Eastern Rural, (v) Western Rural, and (vi) Northern Rural.

Prior to the start of the 2005-09/10 field work, 2 UNPS households were also randomly selected in each EA for the purposes of tracking baseline individuals that moved away from original locations since the UNHS 2005-06. The initial UNPS sample was subject to three consecutive waves of data collection after which, parts of the sample was replaced by new households extracted from the updated sample frames developed by the UBOS as part of the 2012 Uganda Population and Housing Census. In addition, the UNPS will fit within the Long-Term Census and Household Survey Program and therefore both the questionnaires and the timing of data collection will be coordinated with the current surveys and census implemented by UBOS.

Note: Detailed description of sampling procedure and calculation of panel weights is presented in "Basic Information Document". The document is provided along with this metadata.

Mode of data collection

Face-to-face [f2f]

Research instrument

The UNPS survey was collected using the following five questionnaires: 1. Household Questionnaire 2. Woman Questionnaire 3. Agriculture Questionnaire, (administered to the subset of UNPS households engaged in agricultural activities) 4. Community Questionnaire 5. Market Questionnaire.

Abstract

The overall objective of the UNPS Program is to collect high quality data on key outcome indicators such as poverty, service delivery, governance and employment among others; to monitor Government's development programmes like the NDP and the JAF among others on an annual basis. The specific objectives of the survey are: - To provide information required for monitoring the NDP and other development objectives like the JAF, MDGs as well as specific programs such as the National Agricultural Advisory Services (NAADS) among others. - To provide high quality nationally representative information on income dynamics at the household level as well as annual consumption expenditure estimates to monitor poverty in years between the Uganda National Household Surveys (UNHS) - To supply regular data on agriculture in order to characterize and monitor the performance of the agricultural sector.

Geographic coverage

National coverage

Analysis unit

• Household
• Individual / Person
• Woman aged 15-49
• Community

Sampling procedure

The 2011/12 UNPS survey maintained the 2010/11 UNPS sample design whereby all households that were sampled for Wave II (2010/11) were tracked and re-interviewed in Wave III (2011/12). Out of the 7,400 households interviewed during the UNHS 2005/06, 3,123 households were selected for the panel surveys. As a result, the same sample was maintained in 2009/10, 2010/11 and 2011/12 round of surveys. During data collection, households or individuals that had permanently left the original households to known locations were tracked and interviewed. The new households formed are known as split-off households whereas the individuals are termed as movers.

Mode of data collection

Face-to-face [f2f]

Research instrument

The 2011/12 UNPS questionnaires comprised of the following survey instruments: 1) Household Questionnaire: Core and rotating modules 2) Agriculture Questionnaire (for the subset of UNPS households engaged in agricultural activities) 3) Price Questionnaire 4) Community / Facility Questionnaires for schools, health facilities and other facilities (potentially conducted on a rotating basis and not in every year of the UNPS)

Cleaning operations

The 2011/12 round of UNPS used a computerized system of data collection whereby field staff directly captured information using Ultra Mobile Personal Computers (UMPCs) during data collection. The UMPCs were loaded with a data entry application with in-built range and consistency checks to ensure good quality data. Field Team Leaders run checks on the data while still in the field thereafter electronically transmitting it to UBOS Headquarters for verification. Every team was facilitated with an internet modem, a generator and extra UMPC batteries to ensure uninterrupted power supply and internet connectivity while in the field.

Abstract

The 2005-2009/10 Uganda National Panel Survey (UNPS) is the first "panel" survey done by the LSMS group. The households included were chosen from the 2005-2006 Uganda National Household Survey (UNHS).The sample One of the primary uses of the UNPS is to inform policymaking in advance of the Budget, through descriptive reports that are made ready in time for the initial work on sector budget framework papers. The UNPS aimed at producing annual estimates of outcomes and output in the key policy areas and at providing a platform for the experimentation and assessment of national policies and programs. Explicitly, the objectives of the UNPS include:

1. To provide information required for monitoring the National Development Strategy, of major programs such as National Agricultural Advisory Services (NAADS) and General Budget Support, and also to provide information to the compilation of the National Accounts (e.g. agricultural production).
2. To provide high quality nationally representative information on income dynamics at the household level and provide annual information on service delivery and consumption expenditure estimates to monitor poverty and service outcomes in interim years of other national survey efforts, such as the Uganda National Household Survey (UNHS), Uganda Demographic and Health Survey (UDHS) and National Service Delivery Surveys (NSDS).
3. To provide a framework for low-cost experimentation with different policy interventions to e.g. reduce teacher absenteeism, improve ante- and post-natal care, or assessing the effect of agricultural input subsidies.
4. To provide a framework for policy-oriented analysis and capacity building substantiated with the UGDR and support to other research which will feed into the Annual Policy Implementation Review.
5. To facilitate randomized impact evaluations of interventions whose effects cannot currently be readily assessed through the existing system of national household surveys.

Geographic coverage

National

Analysis unit

Households

Kind of data

Sample survey data [ssd]

Sampling procedure

Survey Design The UNPS is carried out annually, over a twelve-month period on a nationally representative sample of households, for the purpose of accommodating the seasonality associated with the composition of and expenditures on consumption. The survey is conducted in two visits in order to better capture agricultural outcomes associated with the two cropping seasons of the country. The UNPS will therefore interview each household twice each year, in visits six months apart. Starting in 2005-09/10, the UNPS has been set out to track and re-interview 3,123 households that were distributed over 322 enumeration areas (EAs), selected out of the 783 EAs that had been visited by the Uganda National Household Survey (UNHS) in 2005-06. The UNPS EAs covered all 34 EAs visited by the UNHS 2005-06 in Kampala District, and 72 EAs (58 rural and 14 urban) in each of the (i) Central Region with the exception of Kampala District, (ii) Eastern Region, (iii) Western Region, and (iv) Northern Region.

Within each stratum, the UNPS EAs were selected from the UNHS 2005-06 EAs with equal probability, and with implicit stratification by urban/rural and district (in this order), except for the rural portions of the ten districts that were oversampled by the UNHS 2005-06. In these districts, the probabilities were deflated, to bring them back to the levels originally intended. Since IDP camps are now mostly unoccupied, the extra EAs in IDP camps are not a part of the UNPS subsample. This allocation strives for reasonably reliable estimates for the rural portion of each region, and for the set of urban areas out of Kampala as a whole, as well as the best possible estimates for Kampala that can be expected from a subsample of the UNHS 2005-06. Therefore, the UNPS strata of representativeness include (i) Kampala City, (ii) Other Urban Areas, (iii) Central Rural, (iv) Eastern Rural, (v) Western Rural, and (vi) Northern Rural.

Prior to the start of the 2005-09/10 field work, 2 UNPS households were also randomly selected in each EA for the purposes of tracking baseline individuals that moved away from original locations since the UNHS 2005-06. The initial UNPS sample was subject to three consecutive waves of data collection after which, parts of the sample were replaced by new households extracted from the updated sample frames developed by the UBOS as part of the 2012 Uganda Population and Housing Census. In addition, the UNPS will fit within the Long-Term Census and Household Survey Program and therefore both the questionnaires and the timing of data collection will be coordinated with the current surveys and census implemented by UBOS.

Note: Detailed description of sampling procedure and calculation of panel weights is presented in "Basic Information Document". The document is provided along with this metadata.

Mode of data collection

Face-to-face [f2f]

Cleaning operations

To ensure good quality of data, a system of double entry was used for data capture. A manual system of editing questionnaires was set-up and two office editors were recruited to further assess the consistency of the data collected. A computer program (hot-deck scrutiny) for verification and validation was developed and operated during data processing. Range and consistency checks were included in the data-entry program. More intensive and thorough checks were carried out using MS-ACCESS by the data processing team.

Sampling error estimates

The estimates presented in the reports of this study were derived from a scientifically selected sample and analysis of survey data was undertaken at national and regional levels. Standard Errors (SE) and Coefficients of Variations (CVs) of some of the variables have been presented in Appendix 2 to show the precision levels.

This file contains data on Ugandan households from six nationwide surveys conducted between 1992 and 2013. Data is available on aggregate household consumption, earnings activities, location of the household, and characteristics of the household head. The file also contains cohort level data where household have been aggregated into cohorts for pseudo-panel analysis.

National household surveys have become the standard source of data for analysis of poverty in developing countries. A major limitation of these surveys for Africa, in terms of the potential to analyse poverty dynamics, is that they are not a panel - different households are surveyed in each wave so they constitute repeated cross sections. It is therefore not possible to track the same households over time to investigate the drivers of poverty reduction. This creates challenges for analysis with endogenous variables, such as interactions between household size and poverty or migration, remittances and household income. The absence of a panel also limits analysis of determinants of household welfare over long periods. The strategy we propose to address this data restriction is to identify representative household types to construct pseudo panels making use of the repeated cross section household surveys (see the Case for Support). Analysis of the pseudo panel allows one to track similar households and complements household-level analysis for each survey. The project will develop methods for constructing pseudo-panels that can be applied, with suitable modifications for specific features of the surveys, in any country with three or more national household surveys. In principle, the methods are also applicable to census and Demographic and Health Survey data. Although the project focuses on Uganda (1992-2012 using eight existing surveys), the methods for constructing and analysing pseudo-panels can be applied to other African countries. Utilising established links with local research partners, hence largely 'off-budget', the pseudo-panel method will be applied to Ghana (1991-2013 using 6 surveys) and Tanzania (1991-2012 using 4 surveys).These three countries all have managed to roughly halve headcount poverty since the early 1990s. We use the repeated cross-section survey data to form a pseudo panel of 'representative' households by grouping individual households (the observational units) into cohorts on the basis of time invariant characteristics (location, gender and birth cohort of household head). The cohorts are then traced over time as they appear in successive surveys, forming a pseudo panel with 'lagged values'. As the cohort fixed effect is correlated with cohort (household) characteristics that are unobserved and not constant over time due to the changing membership of the cohorts in each survey, an errors-in-variables estimator is used to correct the cohort means as estimates of the unobservable population means. The lagged dependent variable is constructed from an auxiliary regression with an augmented instrumental variables estimator using time-invariant instruments. The pseudo panel therefore permits a long (20 years or more) analysis of determinants of household welfare and poverty reduction, with the potential to generate internal instruments for endogenous variables and to identify effects of policy changes (such as Universal Primary Education in Uganda).

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

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 “Uganda - National Panel Survey 2019-2020” and “Uganda - High-Frequency Phone Survey on COVID-19 2020-2021” documentations available in the Microdata Library for details.

Mode of data collection

Computer Assisted Personal Interview [capi]

Cleaning operations

Uganda National Panel Survey 2019-2020 and Uganda High-Frequency Phone Survey on COVID-19 2020-2021 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 “Uganda - National Panel Survey 2019-2020” and “Uganda - High-Frequency Phone Survey on COVID-19 2020-2021” documentations available in the Microdata Library for details.

The Uganda Integrated Household Survey (IHS) was conducted in 1992/93 and was the first national survey conducted in Uganda of its type containing detailed information on households and communities. This project took the original Integrated Household Survey data files, which were catalogued in varying formats and converted them into Stata data files for public usage. The Stata files have been cleaned and coded to ensure ease of usage and understanding.

National household surveys have become the standard source of data for analysis of poverty in developing countries. A major limitation of these surveys for Africa, in terms of the potential to analyse poverty dynamics, is that they are not a panel - different households are surveyed in each wave so they constitute repeated cross sections. It is therefore not possible to track the same households over time to investigate the drivers of poverty reduction. This creates challenges for analysis with endogenous variables, such as interactions between household size and poverty or migration, remittances and household income. The absence of a panel also limits analysis of determinants of household welfare over long periods. The strategy we propose to address this data restriction is to identify representative household types to construct pseudo panels making use of the repeated cross section household surveys (see the Case for Support). Analysis of the pseudo panel allows one to track similar households and complements household-level analysis for each survey. The project will develop methods for constructing pseudo-panels that can be applied, with suitable modifications for specific features of the surveys, in any country with three or more national household surveys. In principle, the methods are also applicable to census and Demographic and Health Survey data. Although the project focuses on Uganda (1992-2012 using eight existing surveys), the methods for constructing and analysing pseudo-panels can be applied to other African countries. Utilising established links with local research partners, hence largely 'off-budget', the pseudo-panel method will be applied to Ghana (1991-2013 using 6 surveys) and Tanzania (1991-2012 using 4 surveys).These three countries all have managed to roughly halve headcount poverty since the early 1990s. We use the repeated cross-section survey data to form a pseudo panel of 'representative' households by grouping individual households (the observational units) into cohorts on the basis of time invariant characteristics (location, gender and birth cohort of household head). The cohorts are then traced over time as they appear in successive surveys, forming a pseudo panel with 'lagged values'. As the cohort fixed effect is correlated with cohort (household) characteristics that are unobserved and not constant over time due to the changing membership of the cohorts in each survey, an errors-in-variables estimator is used to correct the cohort means as estimates of the un-observable population means. The lagged dependent variable is constructed from an auxiliary regression with an augmented instrumental variables estimator using time-invariant instruments. The pseudo panel therefore permits a long (20 years or more) analysis of determinants of household welfare and poverty reduction, with the potential to generate internal instruments for endogenous variables and to identify effects of policy changes (such as Universal Primary Education in Uganda).

Abstract

The Uganda National Household Survey (UNHS) 1999/2000 aims to provide estimates of area and production of major crops and other characteristics of the agricultural enterprises at national, regional and to a limited extent, some district level estimates. In addition, the survey findings will provide insights to the effects of various Government policy measures and programmes at household and community levels. Moreover, the results would assist in addressing specific needs of different users and also to fill in gaps in the socioeconomic indicators for monitoring development performance.

The UNHS 1999/2000 covered all districts except Kitgum, Gulu, Kasese and Bundibugyo. The results therefore do not portray the situation prevailing in these districts. That notwithstanding, the estimates are generally representative of the prevailing situation in the country.

The specific objectives of the survey are as follows: - To plan, design and conduct a country-wide crop farming survey through the household approach. This will provide estimates of area and production of major crops and other characteristics of the agricultural enterprise at national and regional levels including district level estimates for some districts; - Integrate household socio-economic and LC 1 level community surveys in the total survey programme to provide an integrated data-set so as to understand the mechanisms and effects of structural adjustment programmes and other government policy measures on a comparative basis over time; - Meet special data needs of users such as the Ministry of Health, Nutrition and Early Childhood Development Project (NECDP), National Council for Children (NCC), and others, in order to monitor the progress and/or act as a base-line for their project activities and interventions aimed at improvement of child health and mother care; - Fill in gaps in the socio-economic data to serve needs of planning and building social and economic indicators to monitor the progress towards development goals of the country, and to consolidate efforts being made in building a permanent national survey capability in UBOS.

Geographic coverage

The UNHS 1999/00 covered all districts in the country, except the districts of Kitgum, Gulu, Kasese and Bundibugyo.

Analysis unit

• Individuals
• Households
• Communities
• Consumption expenditure commodities/ items

Universe

The survey covered the following populations: - All the resident population with the exception of the nomads, homeless, and refugees - Women aged 12 years and above - Children under 5 years

Kind of data

Sample survey data [ssd]

Sampling procedure

Sampling Design The sampling design adopted for the survey is similar to what was used for the Integrated Household Survey (IHS) 1992/93 and the subsequent monitoring surveys. It is typically a stratified two-stage sampling design except in some districts where the sample was selected in three stages due to lack of an Enumeration Area (EA) frame.

The first stage sampling unit was the EA of the 1991 Population Census in districts with two-stage sampling design, and households as the second stage sampling units. For districts with a three stage design, the first stage sampling units was the parish, while the second stage sampling unit was the LC 1 (village) and the third stage sampling unit is the household.

The survey included panel EA’s and panel households from the 1992/93 Integrated Household Survey as well as new EA’s and new households. In implementing this rather complicated design, services of a Survey Design Consultant were utilised.

Stratification The sampling frame is divided into fairly homogeneous strata in order to improve the efficiency of the sampling design. The first level of stratification is also designed to provide separate and reliable estimates of several parameters for the different domains of interest. In addition to national level estimates, separate estimates are desired for the urban and rural sectors of the statistical regions and 16 selected districts. All districts were sub-stratified into urban, other urban and rural areas (with the exception of Kampala, which is wholly urban). The district headquarters are designated as urban and other urban areas are the town boards, trading centres, etc. as defined during the 1991 Population Census.

To increase the efficiency of the domain estimates, a second level of stratification is created by dividing the domains into homogeneous strata and selecting samples from each stratification. Within the selected rural EA’s, households are classified as small scale farmers, large scale farmers and non-farming households (details stated under Listing below). It should be noted, however, that this stratification is not intended for the purpose of producing reliable estimates for each stratification separately, but only to increase the precision of the rural estimates.

Sampling Frame The sampling frame is made up of EA’s from the 1991 Population Census which were provided at district level with their corresponding number of households. Additionally, the IHS, 1992/93 provided the sampling frame for the panel EA’s and subsequently, the panel households.

Sample Size The size required for a sample is determined by taking into consideration several factors, the three most important being: the degree of precision (reliability) desired for the survey estimates, the cost and operational limitations, and the efficiency of the design.

In the case of UNHS 1999/00, cost and operational limitations allowed a maximum sample size of approximately 10,700 households.

The precision of survey estimates in a domain is a function of the sample size in the domain and the amount of variability among the population units in the domain. Since there are no available estimates of the variance of the different characteristics of interest within the domains for which similar levels of precision for the domains are desirable, a more or less equal allocation was used. Initially a total sample of 1,400 first stage sampling units were selected based on cost and efficiency. These comprised of a common panel from IHS of 637 first stage units selected by simple random sampling and a new independent sample of 773 first stage sampling units selected by probability proportional to the number of households from the Census frame.

Due to some constraints including late procurement of field vehicles, the sample size was reduced proportionately to about 1,100 first stage sampling units. The adjusted sample comprises of about 518 panel EA’s and 563 new EA’s.

Detailed information on the sampling procedure is available in 'Socio-Economic Report'

Sampling deviation

The UNHS 1999/2000 covered all districts in the country, except the districts of Kitgum, Gulu, Kasese and Bundibugyo. The report therefore has quantitative analysis exclusive of these four districts.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaires for the UNHS were based on the previous Household Survey Questionnaires with some modifications and additions. A household questionnaire was administered in each household, which collected various information on household members including duration of stay in household, relationship to household head, sex, age, literacy, marital status, activity status and orphanhood status. The household questionnaire also includes education, and health, characteristics of dwelling, past experiences of dwelling, and household consumption and non - consumption expenditure modules. Questions were also asked in each household for women aged 15-49 and children under age five. For children, the questions were answered by the mother or caretaker of the child.

Cleaning operations

A manual system of editing questionnaires was set-up in September 1999 (a month after commencement of fieldwork). A set of scrutiny notes to guide in manual checking was developed to assess the consistency of the data collected. This is referred to as cold-deck scrutiny. A computer program (hot-deck scrutiny) for verification and validation was developed and operated during data processing. In addition, a set of matching-rules for the panel households was developed in September 1999. These were straightforward by using four variables namely; name, sex, age and education of the head of household. The matching exercise as well as manual scrutiny was a continuous process, which was finally accomplished in September 2000.

Abstract

This data is from the first round of a unique, cross-country panel survey conducted in Sri Lanka by the Secure Livelihoods Research Consortium (SLRC). The Overseas Development Institute (ODI) is the lead organisation of SLRC. SLRC partners who participated in the survey were: the Centre for Poverty Analysis (CEPA) in Sri Lanka, Feinstein International Center (FIC, Tufts University), the Sustainable Development Policy Institute(SDPI) in Pakistan, Humanitarian Aid and Reconstruction, based at Wageningen University (WUR) in the Netherlands, the Nepal Centre for Contemporary Research (NCCR), and the Food and Agriculture Organization (FAO).

This survey generated the first round of data on people's livelihoods, their access to and experience of basic services, and their views of governance actors. SLRC will attempt to re-interview the same respondents in 2015 to find out how the livelihoods and governance perceptions of people shift (or not) over time, and which factors may have contributed towards that change.

Geographic coverage

Regional

Analysis unit

Households

Universe

Randomly selected households in purposely sampled sites (sampling procedure varied slightly by country). Within a selected household, only one household members was interviewed about the household. Respondents were adults and we aimed to interview a fairly even share of men/ women. In some countries this was achieved, but in other countries the share of male respondents is substantially higher (e.g. Pakistan).

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling strategy was designed to select households that are relevant to the main research questions and as well as being of national relevance, while also being able to produce statistically significant conclusions at the study and village level. To meet these objectives, purposive and random sampling were combined at different stages of the sampling strategy. The first stages of the sampling process involved purposive sampling, with random sampling only utilized in the last stage of the process. Sampling locations were selected purposely (including districts and locations within districts), and then randomly households were selected within these locations. A rigorous sample is geared towards meeting the objectives of the research. The samples are not representative for the case study countries and cannot be used to represent the case study countries as a whole, nor for the districts. The samples are representative at the village level, with the exception of Uganda.

Sampling locations (sub-regions or districts, sub-districts and villages) were purposively selected, using criteria, such as levels of service provision or levels of conflict, in order to locate the specific groups of interest and to select geographical locations that are relevant to the broader SLRC research areas and of policy relevance at the national level. For instance, locations experienced high/ low levels of conflict and locations with high/ low provision of services were selected and locations that accounted for all possible combinations of selection criteria were included. Survey locations with different characteristics were chose, so that we could explore the relevance of conflict affectedness, access to services and variations in geography and livelihoods on our outcome variables. Depending on the administrative structure of the country, this process involved selecting a succession of sampling locations (at increasingly lower administrative units).

The survey did not attempt to achieve representativeness at the country /or district level, but it aimed for representativeness at the sub-district /or village level through random sampling (Households were randomly selected within villages so that the results are representative and statistically significant at the village level and so that a varied sample was captured. Households were randomly selected using a number of different tools, depending on data availability, such as random selection from vote registers (Nepal), construction of household listings (DRC) and a quasi-random household process that involved walking in a random direction for a random number of minutes (Uganda).

The samples are statistically significant at the survey level and village level (in all countries) and at the district level in Sri Lanka and sub-region level in Uganda. The sample size was calculated with the aim to achieve statistical significance at the study and village level, and to accommodate the available budget, logistical limitations, and to account for possible attrition between 2012-2015. In a number of countries estimated population data had to be used, as recent population data were not available. The minimum overall sample size required to achieve significance at the study level, given population and average household size across districts, was calculated using a basic sample size calculator at a 95% confidence level and confidence interval of 5. The sample size at the village level was again calculated at the using a 95% confidence level and confidence interval of 5. . Finally, the sample was increased by 20% to account for possible attrition between 2012 and 2015, so that the sample size in 2015 is likely to be still statistically significant. The overall sample required to achieve the sampling objectives in selected districts in each country ranged from 1,259 to 3,175 households.

Mode of data collection

Face-to-face [f2f]

Cleaning operations

CSPro was used for data entries in most countries.

Data editing took place at a number of stages throughout the processing, including: - Office editing and coding - During data entry - Structure checking and completeness - Extensive secondary editing conducted by ODI

Response rate

approximately 99

Sampling error estimates

No further estimations of sampling error was conducted beyond the sampling design stage.

Data appraisal

Done on an ad hoc basis for some countries, but not consistently across all surveys and domains.

Abstract copyright UK Data Service and data collection copyright owner. The Secure Livelihoods Research Consortium Panel Survey, 2012-2018 is a three-wave individual panel survey (2012/13, 2015 and 2018) conducted in three countries, and two-wave individual panel survey (2012 and 2015) in two countries, by the Secure Livelihoods Research Consortium (SLRC). The SLRC is an eight-year global research programme exploring livelihoods, basic services and social protection in conflict-affected situations. SLRC was established in 2011 with the aim of strengthening the evidence base and informing policy and practice around livelihoods and services in conflict. A separate dataset exists for each of the five countries: Democratic Republic of Congo (DRC) (two waves), Nepal (three waves), Pakistan (three waves), Sri Lanka (two waves), and Uganda (three waves). This survey generated two or three rounds of data on people's livelihoods, their access to and experience of basic services, experience of shocks and crimes and of food insecurity, their asset wealth, ownership of land and farming inputs, access to social protection and livelihood assistance, and their views of governance actors. These data provide information at two or three periods in time on individual respondents and on their household members who remained in the same dwelling as the respondent. Households were selected using different sampling methods in each country and, as such, are representative at different levels. The survey is broadly the same in each country and is the same across waves, with some minor exceptions. In particular, the third wave included additional modules to capture individuals' notions of state legitimacy and behaviour. Latest edition informationFor the second edition (August 2021) the data files for Nepal, Uganda and Pakistan were replaced with updated versions containing data for 2012, 2015 and 2018 and the documentation was also updated accordingly. The data and documentation for Democratic Republic of Congo and Sri Lanka still cover 2012 and 2015 only. Main Topics: This study covers the following topics: perceptions of government actors and legitimacy of state in fragile and conflict-affected settings; livelihoods within the household; food insecurity; asset wealth; access to healthcare, education, and water; satisfaction with healthcare, education, and water; social protection and livelihood assistance transfers; coping strategies in response to shocks and crimes; perceptions of safety at the local level. Multi-stage stratified random sample Face-to-face interview: Computer-assisted (CAPI/CAMI) Face-to-face interview: Paper-and-pencil (PAPI)

Abstract

The Uganda Bureau of Statistics (UBOS), on behalf of the Northern Uganda Social Action Fund (NUSAF) under the Office of the Prime Minister conducted the Northern Uganda Survey between August and December 2004.

The survey covered all the 18 districts within the NUSAF region namely, West Nile (covering; Adjumani, Arua, Moyo, Nebbi and Yumbe); Acholi (comprising Gulu, Kitgum and Pader); Lango (consisting of Apac and Lira); Teso (comprising Kaberamaido, Katakwi, Kumi, Soroti and Pallisa); Karamoja (consisting of Kotido,Moroto, Nakapiripirit).

The main objective of the Northern Uganda Survey (NUS) was to collect high quality and timely data on demographic and socio-economic characteristics of household population for monitoring development performance as well as providing baseline indicators for the different socio- economic and vulnerable groups.

The total estimated population in the NUSAF region was 7.1 million persons.Overall, about 53 percent of the population was aged below 15 years. An average household size of 5.2 persons was revealed, similar to that revealed by the 2002 Population and Housing Census for the Northern region. Findings show that the literacy rate for males (68 percent) was higher than that of females (41 percent). Of all persons aged 6-25 years, about 14 percent had no formal schooling. About one in every ten children who had left school was an orphan. About 26 percent of the study population reported at least one illness or symptom in the thirty days preceding the survey. This finding is consistent with the NSDS 2004 where incidence of sickness was reported at 26 percent in the northern region.

The Labour-force participation rate was 67 percent. The monthly household consumption expenditure in the NUSAF region (Shs.72,800) was lower than the national monthly consumption expenditure (Shs.139,300) recorded in UNHS 2002/03. In the NUSAF region, most houses were grass thatched and had walls made of either un-burnt bricks and mud, or poles and mud. The majority of households in the NUSAF region have access to safe drinking water.Households that had experienced shocks were asked to state a maximum of three shocks in descending order of severity. Rebel attacks emerged as the most serious household shock (36 percent) followed by drought or famine (32 percent). Communities had poor access to Agricultural input markets as well as other financial services.

Geographic coverage

The survey covered all the 18 districts within the NUSAF region namely, West Nile (covering; Adjumani, Arua, Moyo, Nebbi and Yumbe); Acholi (comprising Gulu, Kitgum and Pader); Lango (consisting of Apac and Lira); Teso (comprising Kaberamaido, Katakwi, Kumi, Soroti and Pallisa); Karamoja (consisting of Kotido, Moroto, Nakapiripirit)

Analysis unit

• Communities
• Households
• Individuals

Universe

The survey covered all usual residents.

Kind of data

Sample survey data [ssd]

Sampling procedure

The NUS sample was drawn through a stratified two-stage sampling design. The Enumeration Area (EA) was the first-stage sampling unit and the household was the second-stage sampling unit. The sampling frame used for selection of first stage units (fsus) was the list of EAs with the number of households based on the 2002 Population and Housing Census. In order to select the second stage units,which are the households, a listing of households was done in all selected EAs.In the case of the camps, the first stage consisted of selecting IDP camps based on the population in each IDP camp. Each IDP camp is divided into blocks/zones and a sample of blocks was selected using simple random sampling. Within each block, households were selected and interviewed. The details of the sampling design are given in Appendix I of the NUS Report in External Resources.

The size required for the sample was determined by taking into consideration the degree of precision (reliability) desired for the survey estimates, the cost and operational limitations, and the efficiency of the design. NUS covered a sample size of 4787 households in 479 communities (EAs). Of these, about 900 households were in IDP camps. In addition, about 262 households in 100 Enumeration Areas were panel households (interviewed in the 1999, and where possible, 1992 household surveys).

Mode of data collection

Face-to-face [f2f]

Research instrument

Two questionnaires were administered, namely a community questionnaire and a socio-economic questionnaire.

The socio-economic questionnaire included a section on vulnerability and addressed matters relating to internally displaced persons (IDPs), children who have been abducted (ex-abductees), youth who have given up arms for peaceful livelihood alternatives (gun drop outs), youth whose lives have been disrupted by long civil strife, the aged, members of female headed households, and orphans. This module also covered the following areas: health of household members, disability, education, migration, housing conditions, household and enterprise assets, household shocks,and consumption expenditure.

The community questionnaire addressed community facilities including access to schools, health centers, roads, extension services and markets. It also addressed major community events, land tenure, community history, social capital, community projects undertaken and characteristics of the education and health infrastructure used by the community.

Cleaning operations

All questionnaires for NUS 2004 were returned to UBOS for processing. The questionnaires were manually edited using a set of scrutiny notes to guide the manual checking. In addition, range and consistency checks were included in the data-entry computer program. More intensive and thorough checks were carried out using MS-ACCESS.

Response rate

The response rate for the NUS 2004 was about 98 percent. A total of 4787 households were interviewed out of the 4888 households initially targeted. Non-response mainly resulted from insecurity, out migration and resettlement into IDP camps.

As part of an IFPRI-funded project, raw and partially processed secondary data have been harmonized and analyzed to examine the effects of weather variability on household welfare, the latter measured using per capita total household expenditure. This cross-country project covers rural Ghana, Uganda, and Tanzania. Household survey data, a time series of monthly precipitation and temperature, as well as other biophysical data have been harmonized and analyzed using Stata software. Several Stata do files have been created for data processing and analysis as noted in the attached “READ ME.txt” file. The sources of household survey data are the following: National Household Budget Surveys and National Panel Surveys (for Tanzania); National Household Surveys and National Panel Surveys (for Uganda); and Ghana Living Standards Surveys (for Ghana). Precipitation data are obtained from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS). Temperature data are obtained from the Center for Climatic Research at the University of Delaware. Other landscape-level biophysical data analyzed include night lights, population density, and agroecological zones (AEZ).

The primary purpose of the Local Capacity Initiative (LCI) evaluation, including the Uganda case study, was to foster learning about how policy advocacy activities can contribute to increased access to quality HIV services for key populations and vulnerable groups. Public officials who were targeted by the LCI intervention were included in a survey. The goal of the survey was to assess the degree to which LCI activities have served as a resource to public officials, as well as their knowledge and attitudes towards SWs, MSM, and HIV service provision for these groups. A sampe of public officials were invited to participate at the national and district level. The public officials who were reached in 2016 form a panel that was followed up and re-surveyed in 2018.

Abstract

The integrated Household Survey (IHS) was carried out to get a complete and integrated data set needed to better understand the mechanisms of the adjustment process at the household and community level. The survey covered all the districts of Uganda and was a much more comprehensive survey than the 1989-90 household Budget Survey (HBS) from the point of view of area and subject coverage. IHS consisted of the main integrated survey, covering all socio-economic aspects of households, small-scale establishment and household enterprise survey and community survey at RC 1 level. The data collection for the survey was between March 1992 to March 1993 and it was conducted by the Social Dimensions of Adjustment (SDA) a project of the Statistics Department of the Ministry of Finance and Economic planning. The specific objectives of the IHS are:

1. To plan, design and conduct integrated household community and monitoring surveys and to prepare reports thereon providing a complete and integrated dataset needed to understand the mechanisms and effects of structural adjustment process at the household and community level.
2. To fill-in gaps in socio-economic data and build time-series data relating to key economic indicators to serve needs of planning for social and economic development of the country.
3. To build a permanent national household survey capability in the Statistics Department of the Ministry of Finance and Economic Planning to conduct continuing annual survey programs on important aspects of national economy.

Geographic coverage

National

Analysis unit

• Household
• Individual

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling design adopted for the survey is similar to what was used for the Integrated Household Survey (IHS) 1992/93 and the subsequent monitoring surveys. It is typically a stratified two-stage sampling design except in some districts where the sample was selected in three stages due to lack of an Enumeration Area (EA) frame.

The first stage sampling unit was the EA of the 1991 Population Census in districts with two-stage sampling design, and households as the second stage sampling units. For districts with a three stage design, the first stage sampling units was the parish, while the second stage sampling unit was the LC 1 (village) and the third stage sampling unit is the household. The survey included panel EA's and panel households from the 1992/93 Integrated Household Survey as well as new EA's and new households. In implementing this rather complicated design, services of a Survey Design Consultant were utilized.

The sampling frame is divided into fairly homogeneous strata in order to improve the efficiency of the sampling design. The first level of stratification is also designed to provide separate and reliable estimates of several parameters for the different domains of interest. In addition to national level estimates, separate estimates are desired for the urban and rural sectors of the statistical regions and 16 selected districts. All districts were sub-stratified into urban, other urban and rural areas (with the exception of Kampala, which is wholly urban). The district headquarters are designated as urban and other urban areas are the town boards, trading centers, etc. as defined during the 1991 Population Census.

Mode of data collection

Face-to-face [f2f]

Research instrument

These were the following questionnaires: 1. Community Survey Questionnaire 2. Enterprise Questionnaire - Agriculture (Crop Farming) 3. Establishment Listing Questionnaire 4. Main Questionnaire 5. Enterprise Questionnaire - Agriculture (Other than Crop Farming)

Abstract

The survey was conducted in Uganda between January 2013 and August 2013 as part of the Africa Enterprise Survey 2013 roll-out, an initiative of the World Bank. Data from 640 establishments was analyzed. Stratified random sampling was used to select the surveyed businesses.

The objective of the survey is to obtain feedback from enterprises on the state of the private sector as well as to help in building a panel of enterprise data that will make it possible to track changes in the business environment over time, thus allowing, for example, impact assessments of reforms. Through interviews with firms in the manufacturing and services sectors, the survey assesses the constraints to private sector growth and creates statistically significant business environment indicators that are comparable across countries.

The standard Enterprise Survey topics include firm characteristics, gender participation, access to finance, annual sales, costs of inputs and labor, workforce composition, bribery, licensing, infrastructure, trade, crime, competition, capacity utilization, land and permits, taxation, informality, business-government relations, innovation and technology, and performance measures. Over 90 percent of the questions objectively ascertain characteristics of a country’s business environment. The remaining questions assess the survey respondents’ opinions on what are the obstacles to firm growth and performance. The mode of data collection is face-to-face interviews.

Geographic coverage

National

Analysis unit

The primary sampling unit of the study is an establishment. An establishment is a physical location where business is carried out and where industrial operations take place or services are provided. A firm may be composed of one or more establishments. For example, a brewery may have several bottling plants and several establishments for distribution. For the purposes of this survey an establishment must make its own financial decisions and have its own financial statements separate from those of the firm. An establishment must also have its own management and control over its payroll.

Universe

The whole population, or the universe, covered in the Enterprise Surveys is the non-agricultural private economy. It comprises: all manufacturing sectors according to the ISIC Revision 3.1 group classification (group D), construction sector (group F), services sector (groups G and H), and transport, storage, and communications sector (group I). Note that this population definition excludes the following sectors: financial intermediation (group J), real estate and renting activities (group K, except sub-sector 72, IT, which was added to the population under study), and all public or utilities sectors. Companies with 100% government ownership are not eligible to participate in the Enterprise Surveys.

Kind of data

Sample survey data [ssd]

Sampling procedure

The sample for Uganda was selected using stratified random sampling. Three levels of stratification were used in this country: firm sector, firm size, and geographic region.

Industry stratification was designed in the way that follows: the universe was stratified into three manufacturing industry (food, textiles and garments, other manufacturing) and two service sectors (retail and other services).

Size stratification was defined following the standardized definition for the Enterprise Surveys: small (5 to 19 employees), medium (20 to 99 employees), and large (more than 99 employees). For stratification purposes, the number of employees was defined on the basis of reported permanent full-time workers. This seems to be an appropriate definition of the labor force since seasonal/casual/part-time employment is not a common practice, except in the sectors of construction and agriculture.

Regional stratification for the Uganda ES was defined in six regions (city and the surrounding business area): Jinja, Kampala, Lira, Mbale, Mbarara, and Wakiso.

Uganda Bureau of Statistics database was used as a sampling frame with the aim of obtaining interviews with 600 establishments.

Given the impact that non-eligible units included in the sample universe may have on the results, adjustments may be needed when computing the appropriate weights for individual observations. The percentage of confirmed non-eligible units as a proportion of the total number of sampled establishments contacted for the survey was 2% (36 out of 1,567 establishments).

Mode of data collection

Face-to-face [f2f]

Research instrument

The structure of the data base reflects the fact that 3 different versions of the survey instrument were used for all registered establishments. Questionnaires have common questions (Core module) and respectfully additional manufacturing and retail specific questions. The eligible manufacturing industries have been surveyed using the Manufacturing questionnaire (includes the Core module, plus manufacturing specific questions). Retail firms have been interviewed using the Retail questionnaire (includes the Core module plus retail specific questions) and the residual eligible services have been covered using the Core module only. Each variation of the questionnaire is identified by the index variable, a0.

All variables are named using, first, the letter of each section and, second, the number of the variable within the section, i.e. a1 denotes section A, question 1 (some exceptions apply due to comparability reasons). Variable names proceeded by a prefix "KEN" and "A2F" indicate questions specific to some countries in Africa, therefore, they may not be found in the implementation of the rollout in other countries. All other suffixed variables are global and are present in all country surveys over the world. All variables are numeric with the exception of those variables with an "x" at the end of their names. The suffix "x" denotes that the variable is alpha-numeric. In the implementation of the Africa roll out 2011 an experiment was carried in some of the countries to better estimate the effects of the use of show cards in data collection. In some of the sections (i.e. innovation) the enumerators were trained to alternatively implement the section using either show cards or asking only the questions without showing any cards, please see the variable "cards".

Cleaning operations

Data entry and quality controls are implemented by the contractor and data is delivered to the World Bank in batches (typically 10%, 50% and 100%). These data deliveries are checked for logical consistency, out of range values, skip patterns, and duplicate entries. Problems are flagged by the World Bank and corrected by the implementing contractor through data checks, callbacks, and revisiting establishments.

Response rate

Survey non-response must be differentiated from item non-response. The former refers to refusals to participate in the survey altogether whereas the latter refers to the refusals to answer some specific questions. Enterprise Surveys suffer from both problems and different strategies were used to address these issues.

Item non-response was addressed by two strategies: a- For sensitive questions that may generate negative reactions from the respondent, such as corruption or tax evasion, enumerators were instructed to collect "Refusal to respond" (-8) as a different option from "Don't know" (-9). b- Establishments with incomplete information were re-contacted in order to complete this information, whenever necessary.

Survey non-response was addressed by maximizing efforts to contact establishments that were initially selected for interview. Attempts were made to contact the establishment for interview at different times/days of the week before a replacement establishment (with similar strata characteristics) was suggested for interview. Survey non-response did occur but substitutions were made in order to potentially achieve strata-specific goals.

The number of contacted establishments per realized interview was 0.41. This number is the result of two factors: explicit refusals to participate in the survey, as reflected by the rate of rejection (which includes rejections of the screener and the main survey) and the quality of the sample frame, as represented by the presence of ineligible units. The number of rejections per contact was 0.20.

Abstract

This data is from the first round of a unique, cross-country panel survey conducted in Nepal by the Secure Livelihoods Research Consortium (SLRC). The Overseas Development Institute (ODI) is the lead organisation of SLRC. SLRC partners who participated in the survey were: the Centre for Poverty Analysis (CEPA) in Sri Lanka, Feinstein International Center (FIC, Tufts University), the Sustainable Development Policy Institute(SDPI) in Pakistan, Humanitarian Aid and Reconstruction, based at Wageningen University (WUR) in the Netherlands, the Nepal Centre for Contemporary Research (NCCR), and the Food and Agriculture Organization (FAO).

This survey generated the first round of data on people's livelihoods, their access to and experience of basic services, and their views of governance actors. SLRC will attempt to re-interview the same respondents in 2015 to find out how the livelihoods and governance perceptions of people shift (or not) over time, and which factors may have contributed towards that change.

Geographic coverage

Regional

Analysis unit

Households

Universe

Randomly selected households in purposely sampled sites (sampling procedure varied slightly by country). Within a selected household, only one household members was interviewed about the household. Respondents were adults and we aimed to interview a fairly even share of men/ women. In some countries this was achieved, but in other countries the share of male respondents is substantially higher (e.g. Pakistan).

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling strategy was designed to select households that are relevant to the main research questions and as well as being of national relevance, while also being able to produce statistically significant conclusions at the study and village level. To meet these objectives, purposive and random sampling were combined at different stages of the sampling strategy. The first stages of the sampling process involved purposive sampling, with random sampling only utilized in the last stage of the process. Sampling locations were selected purposely (including districts and locations within districts), and then randomly households were selected within these locations. A rigorous sample is geared towards meeting the objectives of the research. The samples are not representative for the case study countries and cannot be used to represent the case study countries as a whole, nor for the districts. The samples are representative at the village level, with the exception of Uganda.

Sampling locations (sub-regions or districts, sub-districts and villages) were purposively selected, using criteria, such as levels of service provision or levels of conflict, in order to locate the specific groups of interest and to select geographical locations that are relevant to the broader SLRC research areas and of policy relevance at the national level. For instance, locations experienced high/ low levels of conflict and locations with high/ low provision of services were selected and locations that accounted for all possible combinations of selection criteria were included. Survey locations with different characteristics were chose, so that we could explore the relevance of conflict affectedness, access to services and variations in geography and livelihoods on our outcome variables. Depending on the administrative structure of the country, this process involved selecting a succession of sampling locations (at increasingly lower administrative units).

The survey did not attempt to achieve representativeness at the country /or district level, but it aimed for representativeness at the sub-district /or village level through random sampling (Households were randomly selected within villages so that the results are representative and statistically significant at the village level and so that a varied sample was captured. Households were randomly selected using a number of different tools, depending on data availability, such as random selection from vote registers (Nepal), construction of household listings (DRC) and a quasi-random household process that involved walking in a random direction for a random number of minutes (Uganda).

The samples are statistically significant at the survey level and village level (in all countries) and at the district level in Sri Lanka and sub-region level in Uganda. The sample size was calculated with the aim to achieve statistical significance at the study and village level, and to accommodate the available budget, logistical limitations, and to account for possible attrition between 2012-2015. In a number of countries estimated population data had to be used, as recent population data were not available. The minimum overall sample size required to achieve significance at the study level, given population and average household size across districts, was calculated using a basic sample size calculator at a 95% confidence level and confidence interval of 5. The sample size at the village level was again calculated at the using a 95% confidence level and confidence interval of 5. Finally, the sample was increased by 20% to account for possible attrition between 2012 and 2015, so that the sample size in 2015 is likely to be still statistically significant. The overall sample required to achieve the sampling objectives in selected districts in each country ranged from 1,259 to 3,175 households.

Mode of data collection

Face-to-face [f2f]

Cleaning operations

CSPro was used for data entries in most countries.

Data editing took place at a number of stages throughout the processing, including: • Office editing and coding • During data entry • Structure checking and completeness • Extensive secondary editing conducted by ODI

Response rate

Approximately 99 percent

Sampling error estimates

No further estimations of sampling error was conducted beyond the sampling design stage.

Data appraisal

Done on an ad hoc basis for some countries, but not consistently across all surveys and domains.

Abstract

This data is from the first round of a unique, cross-country panel survey conducted in Congo, Dem. Rep. by the Secure Livelihoods Research Consortium (SLRC). The Overseas Development Institute (ODI) is the lead organisation of SLRC. SLRC partners who participated in the survey were: the Centre for Poverty Analysis (CEPA) in Sri Lanka, Feinstein International Center (FIC, Tufts University), the Sustainable Development Policy Institute (SDPI) in Pakistan, Humanitarian Aid and Reconstruction, based at Wageningen University (WUR) in the Netherlands, the Nepal Centre for Contemporary Research (NCCR), and the Food and Agriculture Organization (FAO).

This survey generated the first round of data on people's livelihoods, their access to and experience of basic services, and their views of governance actors. SLRC will attempt to re-interview the same respondents in 2015 to find out how the livelihoods and governance perceptions of people shift (or not) over time, and which factors may have contributed towards that change.

Geographic coverage

Regional

Analysis unit

Households

Universe

Randomly selected households in purposely sampled sites (sampling procedure varied slightly by country). Within a selected household, only one household members was interviewed about the household. Respondents were adults and we aimed to interview a fairly even share of men/ women. In some countries this was achieved, but in other countries the share of male respondents is substantially higher (e.g. Pakistan).

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling strategy was designed to select households that are relevant to the main research questions and as well as being of national relevance, while also being able to produce statistically significant conclusions at the study and village level. To meet these objectives, purposive and random sampling were combined at different stages of the sampling strategy. The first stages of the sampling process involved purposive sampling, with random sampling only utilized in the last stage of the process. Sampling locations were selected purposely (including districts and locations within districts), and then randomly households were selected within these locations. A rigorous sample is geared towards meeting the objectives of the research. The samples are not representative for the case study countries and cannot be used to represent the case study countries as a whole, nor for the districts. The samples are representative at the village level, with the exception of Uganda.

Sampling locations (sub-regions or districts, sub-districts and villages) were purposively selected, using criteria, such as levels of service provision or levels of conflict, in order to locate the specific groups of interest and to select geographical locations that are relevant to the broader SLRC research areas and of policy relevance at the national level. For instance, locations experienced high/ low levels of conflict and locations with high/ low provision of services were selected and locations that accounted for all possible combinations of selection criteria were included. Survey locations with different characteristics were chose, so that we could explore the relevance of conflict affectedness, access to services and variations in geography and livelihoods on our outcome variables. Depending on the administrative structure of the country, this process involved selecting a succession of sampling locations (at increasingly lower administrative units).

The survey did not attempt to achieve representativeness at the country /or district level, but it aimed for representativeness at the sub-district /or village level through random sampling (Households were randomly selected within villages so that the results are representative and statistically significant at the village level and so that a varied sample was captured. Households were randomly selected using a number of different tools, depending on data availability, such as random selection from vote registers (Nepal), construction of household listings (DRC) and a quasi-random household process that involved walking in a random direction for a random number of minutes (Uganda).

The samples are statistically significant at the survey level and village level (in all countries) and at the district level in Sri Lanka and sub-region level in Uganda. The sample size was calculated with the aim to achieve statistical significance at the study and village level, and to accommodate the available budget, logistical limitations, and to account for possible attrition between 2012-2015. In a number of countries estimated population data had to be used, as recent population data were not available. The minimum overall sample size required to achieve significance at the study level, given population and average household size across districts, was calculated using a basic sample size calculator at a 95% confidence level and confidence interval of 5. The sample size at the village level was again calculated at the using a 95% confidence level and confidence interval of 5. Finally, the sample was increased by 20% to account for possible attrition between 2012 and 2015, so that the sample size in 2015 is likely to be still statistically significant. The overall sample required to achieve the sampling objectives in selected districts in each country ranged from 1,259 to 3,175 households.

Mode of data collection

Face-to-face [f2f]

Cleaning operations

CSPro was used for data entries in most countries.

Data editing took place at a number of stages throughout the processing, including: • Office editing and coding • During data entry • Structure checking and completeness • Extensive secondary editing conducted by ODI

Response rate

Approximately 99 percent

Sampling error estimates

No further estimations of sampling error was conducted beyond the sampling design stage.

Data appraisal

Done on an ad hoc basis for some countries, but not consistently across all surveys and domains.