2009 India employment survey representative at district level?


I was wondering if it is possible to derive district-level indicators from the 2009 employment survey for India. The general description of the employment surveys indicates ‘state’ for smallest geography but at the same time there is an indicator for GEOLEV2, which is the district. The general description also seems to refer to the 1983 survey, which is confusing. Hence, I wonder if it is possible to use the given weights to aggregate to the district 2/GEOLEV2 level for the 2009 survey.

Hi Michiel,

Thank you for noting this error in the documentation. The sample information currently only reflects the 1983 survey. District information is indeed available for all samples of the India employment survey aside from the ones fielded in 1983 and 1993. You can find the list of all unharmonized geography variables for your selected samples on this page. You can also use the harmonized second-level geography variable GEOLEV2. Further information about the harmonization process is provided. The estimates you generate using the weights should be representative on the district level, although the variance of your estimates will be inversely proportional to the sizes of your subsamples.