Sampling Procedure
The Quarterly Labour Force Survey (QLFS) uses the 2013 Master Sample, which was developed from the 2011 Population Census as a general-purpose sampling frame for household surveys conducted by Statistics South Africa. The sampling frame is based on 103,576 census enumeration areas (EAs), which were aggregated into 3,324 primary sampling units (PSUs). This represented an 8% increase from the previous 2008 Master Sample to improve the precision of survey estimates by reducing sampling variability. The Master Sample includes approximately 33,000 dwelling units and is designed to produce representative estimates at the national, provincial, metropolitan/non-metropolitan, and geographic-type (urban, tribal, and farm) levels.
The QLFS employs a stratified two-stage sampling design. In the first stage, PSUs are selected using probability proportional to size (PPS) sampling, while in the second stage, dwelling units are selected systematically within each sampled PSU. To support the survey's rotating panel design, the Master Sample is divided equally into four rotation groups, each reflecting the same distribution as the full sample. One rotation group is replaced each quarter, allowing the survey to balance continuity for labour market analysis with the introduction of new households over time.
Please refer to Labour Market Dynamics in South Africa Metadata 2024 (lmdsa-2024-metadata) for more information on sampling.
Weighting
The sample weights were constructed in order to account for the following: the original selection probabilities (design weights); adjustments for PSUs that were sub-sampled or segmented; excluded population from the sampling frame (EAs with insufficient DUs); non-response; weight trimming; benchmarking to known population estimates from the Demographic Analysis Chief Directorate within Stats SA; and raking to bias-adjusted control estimates from a Bias Adjustment procedure to compensate for the non-coverage bias in the sample due to only observing those households that can be contacted by telephone. Please refer to Labour Market Dynamics in South Africa Metadata 2024 (lmdsa-2024-metadata) for more information on weights.
