Afrobarometer uses national probability samples designed to meet the following criteria:
Samples are designed to generate a sample that is a representative cross-section of all citizens of voting age in a given country. The goal is to give every adult citizen an equal and known chance of being selected for an interview. This is achieved by:
- using random selection methods at every stage of sampling;
- sampling at all stages with probability proportionate to population size (PPPS) wherever possible to ensure that larger (i.e., more populated) geographic units have a proportionally greater probability of being chosen into the sample.
- The sampling universe normally includes all citizens age 18 and older. As a standard practice, we exclude people living in institutionalized settings, such as students in dormitories, patients in hospitals, and persons in prisons or nursing homes. In addition, we must occasionally exclude people living in areas determined to be inaccessible due to conflict or insecurity. Any such exclusions will be noted in the Technical Information Report that accompanies each data set.
Sample size and design
- Samples usually include either 1200 or 2400 cases. A randomly selected sample of n=1200 cases allows inferences to national adult populations with a margin of sampling error of no more than +/-2.8% with a confidence level of 95 percent. With a sample size of n=2400, the margin of error decreases to +/-2.0% at 95 percent confidence level.
The sample design is a clustered, stratified, multi-stage, area probability sample. Specifically, we first stratify the sample according to the main sub-national unit of government (state, province, region, etc.) and by urban or rural location.
Area stratification reduces the likelihood that distinctive ethnic or language groups are left out of the sample. Afrobarometer occasionally purposely oversamples certain populations that are politically significant within a country to ensure that the size of the sub-sample is large enough to be analyzed. Any oversamples will be noted in the Technical Information Report that accompanies each data set.
Samples are then drawn in either four or five stages:
- In rural areas only, the first stage is to draw Secondary Sampling Units (SSUs). SSUs are not used in rural areas, and in some countries they are not used in rural areas. See the Technical Information Form for that accompanies each data set for specific details on the sample in any given country.
- The next stage is random selection of primary sampling units (PSU).
- We then randomly select sampling start points.
- Interviewers then randomly select households.
- Within the household, the interviewer randomly selects an individual respondent. Each interviewers alternates in each household between interviewing a man and interviewing a woman to ensure gender balance in the sample.
- To keep the costs and logistics of fieldwork within manageable limits, eight interviews are clustered within each selected PSU.
Based on the sampling methodology used, Afrobarometer data sets can be treated as being approximately self-weighting. However, since Round 4, data sets have included weighting factors at the PSU level to account for individual selection probability. This weighting factor is included as the last variable in each data set, labeled “withinwt”, and it should be applied when calculating national-level statistics for any given country.
- Prior to Round 4, weighting factors are included only where there were oversamples of certain regions or populations.
- Any deviations from standard protocols (e.g., clustering of 4 rather than 8 interviews per PSU in some countries, areas excluded from the sample, purposeful oversamples, etc.) will be recorded in the Technical Information Report that accompanies each data set.
Further information on Round 5 Sampling Protocols, including full details of the methodologies used for each stage of sample selection, can be found in Section 5 of the Afrobarometer Round 5 Survey Manual