Mongolia - HSES 2007/2008

The sampling frame of the HSES was devel­oped by the NSO based on population figures for 2005 from local registration offices. This updated sampling frame is crucial because the spatial distribution of the population had changed dramati­cally over the last years and any frame based on the Census 2000 would have not been relevant anymore.

The design of the survey recognizes three ex­plicit strata: Ulaanbaatar, aimag centers, and ru­ral areas and small towns. In addition, the sample was implicitly allocated by districts and khoroos in Ulaanbaatar, and by aimags in rural areas. Each aimag center was an explicit sub-stratum. The aimag of Govisumber was excluded from the sample due to its small size.

The selection strategy was different in each stratum: a two-stage process in urban areas and a three-stage process in rural areas. In Ulaanbaatar, first 360 khesegs were selected, and then 10 households in each kheseg. In aimag centers, first 12 or 24 bags were selected, and then 10 house­holds in each bag.35 In rural areas, first 52 soums were selected, then 12 bags in each soum and fi­nally 8 households in each bag. All 1,248 primary sampling units or clusters (khesegs, bags or soums) were selected with probability proportional to size and were randomly allocated into the 12 months of survey fieldwork. Thus the survey visited a ran­dom sub-sample of 104 clusters each month.

The use of this sampling procedure means that households living in different areas of the coun­try have been selected with different probabilities. Therefore, in order to obtain representative sta­tistics for each stratum and for the whole coun­try, it is necessary to use sampling weights. These weights are applied to each household and cor­respond to the inverse of the probability of selec­tion, calculated taking into account the sampling strategy.

The sample of 11,232 households was allocated as follows: 3,600 in Ulaanbaatar, 2,640 in aimag centers and 4,992 in rural areas and small towns. However, the actual sample used for this report is slightly lower: 3,571 households in Ulaanbaatar, 2,621 in aimag centers, and 4,980 in rural areas and small towns. The difference corresponds to 60 households that were excluded because they did not have complete information.