Sampling
Sampling Procedure
As the Time Use Survey is a household-based survey, the last-stage sample units are individual households. The sample size was set to be sufficiently representative to estimate population time use indicators at the national level, including urban, rural, and regional areas (Western, Khangai, Central, Eastern, and Ulaanbaatar).
Nationwide, 4,000 households were surveyed, and the number of households in each region was calculated using the square root biased sampling method. Because survey data is collected over four quarters, the sample size is evenly distributed over four quarters.
Multi-stage sampling method was used to select households. In the first round, 2 aimags were selected at random, representing 4 regions except Ulaanbaatar. The number of households selected from the aimags is shown in detail in Table 2.1. In the second stage, the primary sampling unit (PSU) was determined by a probability proportional to size sampling method. In the last stage, 20 households were selected from each PSU using a systematic sampling method. The sampling of households was based on the Population and Household Database as of the first week of March, June, September, and December, when quarterly data collection was conducted.
