Sampling
Sampling Procedure
The sample for the Khuvsgul province CDS was designed to provide estimates for a large number of indicators on the situation of children and women at provincial level , for urban and rural areas, for six regions namely Central, Touristic, Agricultural, Ider, Tes-Ekh and Murun. The regions were identified as the main sampling domains and the sample was selected in two stages. At the first stage the primary sampling units (PSUs) were the baghs in soums in Khuvsgul province.
Deviations from Sample Design
A total of 2650 households were selected and selection probabilities and corresponding weights vary by PSUs and by the second stage stratum of households with and without children under 5 years of age.
Within each sampling stratum, the sample was selected in two stages. The PSUs within each stratum were selected systematically with probability proportional to size (PPS). After a household listing was carried out in each sample PSU, a systematic sample of households was selected separately for households with and without children, for a total of 25 sample households per PSU. The 2015 official statistics of the household registration was used as a sampling frame.
The sample was stratified by region and is not self-weighting. For reporting all survey results, sample weights are used. As it was mentioned before the lowest administrative units (bagh within soum in the province) were defined as primary sampling units. The survey covered 23 soums and 106 sample baghs; the listing of households was updated during September-October 2016.
During the data collection fieldwork in October-December 2016, we had encountered problems due to seasonal movement of families; transportation means to reach remote families were broken due to heavy snow falls and severe cold. In spite of this, we managed to collect survey data in all of the 106 selected PSUs.
