Poverty Income Consumption and Expenditure Survey 2017: Scientific Use File
Zimbabwe
Zimbabwe National Statistical Agency
Identification
idno
ZWE_2017_PICES_v01_M_v0_A_SUF
Title
Poverty Income Consumption and Expenditure Survey 2017: Scientific Use File
Country
| Name | Country code |
|---|---|
| Zimbabwe | ZWE |
Abstract
The Poverty Income, Consumption, and Expenditure Survey (PICES) is the main data source for the compilation of national accounts aggregates and also provides information on living conditions, poverty levels and weights for the consumer price index (CPI).
The objectives of the survey are to provide data to enable:
· estimate private consumption expenditure and disposable income of the household sector;
· compile the production account of the agricultural sector
· study income/expenditure disparities among socio-economic groups
· estimate the contribution of the informal sector to GDP in Zimbabwe
· estimate the size of household transfer incomes within and outside the country;
· calculate weights for the Consumer Price Index (CPI)
· calculate the poverty line, measure the poverty rate and inequality
· provide data useful to formulate national policies for social welfare programmes
· obtain data for poverty mapping
· obtain data useful in measuring the demographic dividend for Zimbabwe
The objectives of the survey are to provide data to enable:
· estimate private consumption expenditure and disposable income of the household sector;
· compile the production account of the agricultural sector
· study income/expenditure disparities among socio-economic groups
· estimate the contribution of the informal sector to GDP in Zimbabwe
· estimate the size of household transfer incomes within and outside the country;
· calculate weights for the Consumer Price Index (CPI)
· calculate the poverty line, measure the poverty rate and inequality
· provide data useful to formulate national policies for social welfare programmes
· obtain data for poverty mapping
· obtain data useful in measuring the demographic dividend for Zimbabwe
Unit of Analysis
Household
Version
Version number
v02 Edited, anonymous dataset for public distribution.
Coverage
Geographic Coverage
National Coverage going to provinces and districts
Unit of Analysis
Household
Universe
Population can be enumerated using two methods: a "de jure" and a "de facto" population count. A " de jure" count is the enumeration of persons, who usually reside in a given place, whereas a "de facto" count is the enumeration of persons physically present at a specified place. For this survey we adopt the "de jure" concept. The usual members may be present or temporarily absent. We are thus concerned about the de jure household. A household is defined as a single person or a group of people who usually live, cook and eat together, they may be related or not.
Producers and sponsors
Authoring entity/Primary investigators
| Agency Name | Affiliation |
|---|---|
| Zimbabwe National Statistical Agency | Ministry of Finance and Economic Development |
Producers
| Name | Role |
|---|---|
| World Bank | Technical Support |
| United Nations Children’s Fund | Technical Support |
| United Nations Development Programme | Technical Support |
| African Developmrent Bank | Technical Support |
| Department for International Development | Technical Support |
| United Nations Population Fund | Technical, Material Support |
| Ministry of Labour and Social Services | Technical, Support |
| Ministry of Finance and Economic Development | Technical, Support |
Funding Agency/Sponsor
| Name | Abbreviation | Role |
|---|---|---|
| World Bank | WB | Financial |
| United Nations Children's Fund | UNICEF | Financial |
| United National Development Programme | UNDP | Financial |
| African Development Bank | AfDB | Financial |
| Government of Zimbabwe | GoZ | Financial |
| United Nations Population Fund | UNFPA | Material Support |
Sampling
Sampling Procedure
The survey is based on a sample of 32,256 households, representative at Province and District Levels. The sample design entailed two stages: selection of enumeration areas (EAs) as the first stage and selection of households in these EAs as the second stage. In total 2,304 EAs are selected with Probability Proportional to Size (PPS), the measure of size being the number of households enumerated in the 2012 Population Census. Out of a total of 32,256 sampled households a total of 31,195 households successfully completed interviews. This gives a response rate of 96.7 percent of the sampled households.
The sampling frame for the PICES 2017 is based on the complete set of Enumeration Areas (EAs) drawn from the 2012 Zimbabwe Population Census. The sample for most national household surveys in Zimbabwe is formed by the Zimbabwe master sample, which is based on the 2012 Population Census frame. However, since many surveys have previously used the Master Sample of EAs, some of the same households could be selected again for the PICES, resulting in an increasing response burden. Consequently, the Zimbabwe Master Sample is not used for the PICES 2017 sample and instead the Population Census Frame is used to draw the sample.
At the second sampling stage, a random systematic sample of 14 households are selected with equal probability from the listing of each sample EA. Reserve households are selected for replacements. The reason why the replacement of non-interview households are considered was to maintain the effective sample size and enumerator workload in each sample EA. Four households are selected for possible replacement, and thus a total of 18 households are selected from each sample EA. A systematic subsample of 4 households are then selected from the 18 households, and the remaining 14 sample households are considered the original sample for the survey.
The sampling frame for the PICES 2017 is based on the complete set of Enumeration Areas (EAs) drawn from the 2012 Zimbabwe Population Census. The sample for most national household surveys in Zimbabwe is formed by the Zimbabwe master sample, which is based on the 2012 Population Census frame. However, since many surveys have previously used the Master Sample of EAs, some of the same households could be selected again for the PICES, resulting in an increasing response burden. Consequently, the Zimbabwe Master Sample is not used for the PICES 2017 sample and instead the Population Census Frame is used to draw the sample.
At the second sampling stage, a random systematic sample of 14 households are selected with equal probability from the listing of each sample EA. Reserve households are selected for replacements. The reason why the replacement of non-interview households are considered was to maintain the effective sample size and enumerator workload in each sample EA. Four households are selected for possible replacement, and thus a total of 18 households are selected from each sample EA. A systematic subsample of 4 households are then selected from the 18 households, and the remaining 14 sample households are considered the original sample for the survey.
Weighting
In order for the sample estimates from the PICES 2017 to be representative of the population, the data is multiplied by a sampling weight, or expansion factor. The basic weight for each sample household would be equal to the inverse of its probability of selection (calculated by multiplying the probabilities at each sampling stage). Additional details on weighting are provided in Section 1.13 of the PICES 2017 Survey Report.
Data Collection
Mode of data collection
Face-to-face [f2f] Interviews on a paper questionnaire. Enumerators left Daily Record Books at households. The Enumerator visited households every week to collect DRBS and to check if the DRBs were being completed by the households.
Metadata production
Document ID
DDI_ZWE_2017_PICES_v01_M_v01_A_SUF
Producers
| Name | Abbreviation | Affiliation | Role |
|---|---|---|---|
| Zimbabwe National Statistics Agency | ZIMSTAT | Ministry of Finance and Economic Development | Documentation of the DDI |