Sampling
Sampling Procedure
The survey was conducted using a two-stage sampling method, with equal probability of selection of households. The sample frame comprised the listings of households prepared annually in bags and horoos across the country. It was determined from experience of other countries that 25 households per cluster would provide an optimum representation in a country where no such survey has ever before been conducted. (The best cluster "take" depends upon the intra-cluster versus inter-cluster heterogeneity of the principal variables being measured; this can only be determined after carrying out a survey.) For the survey it was planned to select 6000 households, which is a 1,13 percent sample of all households in the country. This implied the selection of 240 clusters of households. Bags and horoos were the primary sampling units (PSUs). All 1684 PSUs were stratified implicitly by aimag and soum, and the selection of the 240 sample PSUs (or clusters) was done systematically with a random start, with probability proportional to the number of registered households. Households were then selected systematically with a random start within each PSU, using an interval directly proportional to the number of households in the PSU. Each registered household in Mongolia had an equal and known probability of being selected in the RHS sample. The selected households were interviewed using the household schedule. All women between the ages of 15 and 49, inclusive, who slept in the household's dwelling the night prior to interview were eligible to be interviewed using the women's interview schedule. Interviewing teams were also instructed to interview 6 husbands of interviewed women in each PSU.
Distribution of the RHS Household Sampling by Aimag,
Mongolia 1998
Aimag Clusters Number of Households
1 Arhangai 1-12 300
2 Bayan-Olgii 13-20 200
3 Bayanhongor 21-30 250
4 Bulgan 31-37 175
5 Gobi-Altai 38-44 175
6 Dornogobi 45-49 125
7 Dornod 50-57 200
8 Dundgobi 58-63 150
9 Zavhan 64-73 250
10 Selenge 74-83 250
11 Suhbaatar 84-89 150
12 Uvs 90-99 249
13 Tov 100-110 275
14 Ovorhangai 111-124 350
15 Omnogobi 125-129 125
16 Hovd 130-137 200
17 Hovsgol 138-150 325
18 Hentii 151-158 200
19 Darhan-Uul 159-168 250
20 Orhon 169-174 149
21 Gobisumber 175-176 50
22 Ulaanbaatar 177-240 1607
Total 6005
Response Rate
Results of the Household and Individual Interviews (Women and Husbands),Mongolia 1998
Residence
Urban Rural Total
Number of Dwellings Sampled 2931 3074 6005
Number of Households Interviewed 2930 3073 6003
Household Response Rate 100.0 100.0 100.0
Number of Eligible Women 3943 3610 7553
Number of Eligible Women Interviewed 3904 3557 7461
Eligible Women Response Rate 99.0 98.5 98.8
Number of Husbands Selected 794 766 1560
Number of Husbands Interviewed 793 764 1557
Husbands Response Rate 99.9 99.7 99.8
Weighting
Sampling metod is a nation wide.
