The Ethiopian Socioeconomic Survey (ESS) is a collaborative project between the Central Statistics Agency of Ethiopia (CSA) and the World Bank Living Standards Measurement Study- Integrated Surveys on Agriculture (LSMS-ISA) team. The objective of the LSMS-ISA is to collect multi-topic panel household level data with a special focus on improving agriculture statistics and the link between agriculture and other sectors of the economy. The project also aims to build capacity, share knowledge across countries, and improve survey methodologies and technology.
The specific objectives of the ESS are:
- Development of an innovative model for collecting agricultural data in conjunction with household data;
- Strengthening the capacity to generate a sustainable system for producing accurate and timely information on agricultural households in Ethiopia;
- Development of a model of inter-institutional collaboration between the CSA and relevant federal and local government agencies as well as national and international research and development partners; and
- Comprehensive analysis of household income, well-being, and socio-economic characteristics of households in rural areas and small towns.
The ESS contains several innovative features:
- Integration of household welfare data with agricultural data;
- Creation of a panel data set that can be used to study welfare dynamics, the role of agriculture in development and the changes over time in health, education and labor activities, inter alia;.
- Collection of information on the network of buyers and sellers of goods with which the household interacts;
- Expanding the use of GPS units for measuring agricultural land areas;
- Involvement of multiple actors in government, academia and the donor community in the development of the survey and its contents as well as its implementation and analysis;
- Creation of publicly available micro data sets for researchers and policy makers;
Kind of data
Sample survey data [ssd]
Variable ls_saq08 dropped from sect_cover_ls_w2.dta for confidentiality reasons.
The Ethiopia Socioeconomic Survey 2013/2014 (ESS2) covered all regional states including the capital, Addis Ababa. The majority of the sample comprises rural areas as it was carried over from ESS1. The ESS2 was implemented in 433 enumeration areas (EAs) out of which 290 were rural, 43 were small town EAs from ESS1, and 100 were new EAs from major urban areas.
Unit of analysis
Households, individuals and communities.
Producers and sponsors
Central Statistics Agency of Ethiopia (CSA)
Ministry of Finance and Economic Development
Living Standards Measurement Study Integrated Surveys of Agriculture (LSMS-ISA)
Ministry of Agriculture
Ministry of Finance and Economic Development
Ethiopia Agricultural Transformation Agency
World Food Program
International Food Policy Research Institute
Ethiopia Institute of Agricultural Research
World Bank through Bill and Melinda Gates Foundation
Funded the study
ESS is designed to collect panel data in rural and urban areas on a range of household and community level characteristics linked to agricultural activities. The first wave was implemented in 2011-12 and the second wave is implemented in 2013-14. The first wave, ERSS, covered only rural and small town areas. The second wave, ESS, added samples from large town areas. The second wave is nationally representative. The existing panel data (2011/12-2013/14) is only for rural and small towns. Large towns were added during the second wave and, so far, there is only one round. The planned follow-up ESS surveys will continue to be nationally representative. The ESS sample size provides estimates at the national level for rural and small town households. At the regional level, it provides estimates for five regions including Addis Ababa, Amhara, Oromiya, SNNP, and Tigray.
The sample is a two-stage probability sample. The first stage of sampling entailed selecting primary sampling units, which are a sample of the CSA enumeration areas (EAs). A total of 433 EAs were selected based on probability proportional to size of the total EAs in each region. For the rural sample, 290 EAs were selected from the AgSS EAs. For small town EAs, a total of 43 EAs and for large towns 100 EAs were selected. In order to ensure sufficient sample in the most populous regions (Amhara, Oromiya, SNNP, and Tigray) and Addis Ababa, quotas were set for the number of EAs in each region. The sample is not representative for each of the small regions including Afar, Benshangul Gumuz, Dire Dawa, Gambella, Harari, and Somalie regions. However, estimates can be produced for a combination of all smaller regions as one "other region" category.
During the second wave 100 urban EAs were added. The addition also included one more region to the sample, Addis Ababa. In each EA 15 households were selected. The addition of urban EAs increased the sample size from 333 to 433 EAs or from about 3,969 to 5,469 households.
The second stage of sampling was the selection of households to be interviewed in each EA. For rural EAs, a total of 12 households are sampled in each EA. Of these, 10 households were randomly selected from the sample of 30 AgSS households. The AgSS households are households which are involved in farming or livestock activities. Another 2 households were randomly selected from all other non-agricultural households in the selected rural EA (those not involved in agriculture or livestock). In some EAs, there is only one or no such households, in which case, less than two non-agricultural households were surveyed and more agricultural households were interviewed instead so that the total number of households per EA remains the same.
In the small town EAs, 12 households are selected randomly from the listing of each EA, with no stratification as to whether the household is engaged in agriculture/livestock. The same procedure is followed in the large town EAs. However, 15 households were selected in each large town EA.
Households were not selected using replacement. Thus, the final number of household interviewed was slightly less than the 5,469 as planned in the design. A total of 3,776 panel households and 1,486 new households (total 5,262 households) were interviewed with a response rate of 96.2 percent.
Response rate was 96.2 percent.
The Ethiopia Socioeconomic Survey 2013/2014 data needs to be weighted to represent the national-level population of rural, small and large town households. A sample weight with post-stratification adjustments was calculated for the households and this weight variable is included in all the datasets. It reflects the adjusted probability of selecting the household into the sample. The inverse of this weight can be considered an expansion factor that sums to the total population of households in the nation. When this weight is used in a household-level file, it sums to the population of households. When this weight is used in an individual-level file, it sums to the population of individuals. If the data user wishes to produce an estimate for the population of individuals in a household-level file, an approximate expansion factor is the sample weight times the household size of each household.
The Ethiopia Socioeconomic Survey 2013/2014 sample weights were calculated in two stages. In the first stage, weights were separately calculated or adjusted for the three different sampling frames (rural, small town, and large town20). For the rural sample, the wave 1 weights were adjusted to account for relisting, non-response, and attrition of households in the sample frame (the AgSS) between the two waves. In each of the waves, the rural EAs were re-listed which reflects EA-specific population growth patterns. The post-stratification adjustment accounts for this change. For the small town sample, the EAs were not re-listed so the wave 1 weights were adjusted to reflect national population growth between the two waves.
For the mid- and large-town sample, new weights were calculated in accordance with the sampling design and then adjusted to reflect household listing and nonresponse encountered during field work. The sample weights were estimated as the product of the first-stage of sampling (which was PPS selection of EA) and the second stage of sampling (which was SRS sampling of 15 households within each EA). The first stage selection was based on population estimates. The EAs were listed after selection, and the first-stage probability was adjusted to account for the difference between the listing counts and the EA population estimates used for the first stage selection. The product of the adjusted first stage weight and the second stage weight were then adjusted to account for non-response. Finally, these sampling weights were further post-stratified to ensure that the sum of the weights within each region matched the 2014 population estimates provided by CSA.
Dates of collection
Mode of data collection
Data collection supervision
Fieldwork Monitoring and Evaluation
Routine supervision by CSA's field supervisors entailed the field-level coordination by all CSA branch offices. Branch level statisticians and supervisors who were assigned to this project conducted the routine supervision. The branch supervisors made three extended visits to the EAs between September, 2013 and April, 2014. As noted above, one field supervisor checked the work of three enumerators in three EAs. The last visit was combined with community interviews that were conducted by the supervisors themselves. Up to two branch statisticians were also in the field to check the work of the supervisors and enumerators.
Additional supervision was done by teams composed of the CSA head office experts and Bank staff and consultants, who made two supervision visits. Each visit took about 2 weeks. The first visit was held in September-October 2013 when interviews with the Post-planting questionnaire were being conducted. The second visit was in February-April 2014 when the household, community, and post-harvest agriculture data were being collected.
The survey was collected using five questionnaires: household, community, post-planting agriculture, post-harvest agriculture and livestock questionnaires.
The household questionnaire collected information on basic demographics; education; health (including anthropometric measurement for children); labor and time use; partial food and non-food expenditure; household nonfarm income-generating activities; food security and shocks; safety nets; housing conditions; assets; credit; and other sources of household income. The household questionnaire, when relevant, is comparable to the Welfare Monitoring Survey (WMS).
The community questionnaire gathered information on access to infrastructure; community organizations; resource management; changes in the community; key events; community needs, actions and achievements; and local retail price information.
Post-planting and post-harvest agriculture questionnaires were completed in those households with at least one member of the household engaged in crop farming using owned or rented land The post-planting and post-harvest agriculture questionnaires focused on farming activities and solicit information on land ownership and use; farm labor; inputs use; GPS land area measurement and coordinates of household fields; agriculture capital; irrigation; and crop harvest and utilization.
The livestock questionnaire interviews were implemented in households where at least one member was engaged in livestock rearing. The livestock questionnaire collected information on animal holdings and costs; and production, cost and sales of livestock byproducts.
Central Statistics Agency of Ethiopia
Ministry of Finance and Economic Development
The interviews were carried out using paper and pen interviewing method. However, a concurrent data entry arrangement was introduced in this wave. In this arrangement, the enumerators did not wait until all the interviews were completed. Rather, once the enumerators completed some 3 to 4 questionnaires, the supervisors collected those completed interviews from the enumerators and brought them to the branch offices for data entry, while the enumerators are still conducting interviews with other households. Then questionnaires are keyed at the branch offices as soon as they are completed using CSPro data entry application software. The data from the completed questionnaires are then checked for any interview or data entry errors using a stata program. Data entry errors are checked with the data entry clerks and the interview errors are then sent to back to the field for correction and feedback to the ongoing interviews. Several rounds of this process were undertaken until the final data files are produced. In addition, after the fieldwork was completed the paper questionnaires were sent to the CSA headquarters in Addis Ababa for further checking. Additional cleaning was carried out, as needed, by checking the hard copies.
LSMS Database Manager, Development Research Group
The World Bank
Central Statistical Agency
Use of the dataset must be acknowledged using a citation which would include:
- the Identification of the Primary Investigator
- the title of the survey (including country, acronym and year of implementation)
- the survey reference number
- the source and date of download
Central Statistics Agency of Ethiopia (CSA). Ethiopia Socioeconomic Survey 2013-2014, Ref. ETH_2013_ESS_v02_M. Dataset downloaded from [URL] on [date].
Disclaimer and copyrights
The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
LSMS Data Manager
The World Bank
Development Data Group
The World Bank
Documentation of the DDI
Version 02 (January 2018)
Identical to version 01, updates made to dataset sect_cover_ls_w2.dta