Survey ID Number
KHM_2019_CIAS_v01_EN_M_v01_A_OCS
Title
Cambodia Inter-Censal Agriculture Survey 2019
Sampling Procedure
The sampling frame used for CIAS 2019 listed around 14,000 villages, split in 2 or 3 Enumeration Areas (EAs) each, for a total of 35,000 EAs. For each village, the following information was available: province, district, commune, type (rural/urban), number of EAs and number of households. Given their low number of rural villages, the following districts were excluded from the frame: Province Preah Sihanouk, District Krong Preah Sihanouk, Province Siemreap, District Krong Siem Reab, Province Phnom Penh, District Chamkar Mon, Province Phnom Penh, District Doun Penh, Province Phnom Penh, District Prampir Meakkakra, Province Phnom Penh, District Tuol Kouk, Province Phnom Penh, District Ruessei Kaev, Province Phnom Penh, District Chhbar Ampov
Since the number of rural households per EA was not known, in order to calculate the number of rural households in each province the sum of the households in the villages that were classified as rural was computed. The listing operation in each sampled EA was conducted with the aim of identifying the target population, i.e. the households engaged in agricultural activities.
The adopted sampling design was a two-stage stratified sampling, with EAs as primary units and households engaged in agriculture as secondary units. It was decided to select 1,350 EAs and 12 agricultural households for each EA, for a total planned sample size of 16,000 households. The 1,350 EAs were allocated to the provinces (sampling domains) proportionally to the number of rural households. Since there are no rural villages in Phnom Penh, 50 EAs (that correspond to 60,000 rural households) were allocated to Phnom Penh Province by default and 1,300 EAs were allocated to the other provinces. In order to select the EAs within each province, the villages were ordered by district, then by commune, then by type of village (Rural-Urban) and a systematic sampling was performed, with probability proportional to size (number of households).
The screening procedure conducted in each of the 1,350 selected EAs allowed not only to identify the agricultural holdings, but also to make a partition in strata of the agricultural households in each province and apply a stratified sampling scheme for the secondary units. Details of these strata by province can be found in Annex 3 of the general CIAS 2019 report. Each province could have a different composition and definition of the strata. The units in some strata could all be selected, particularly if they were rare, while in most strata, households were sampled. In general, within provinces, the allocations in each stratum were computed proportionally to the size of the stratum in the population of the selected EAs in the province. Once the stratum allocations in each province were computed, the allocations within the province to the EAs were calculated proportionally to the size of the stratum in the selected EA with respect to the stratum size in the province, under the constraint that the total sampled households for each EA be 12. The total effective sample size of the survey was 15,994 agricultural households. The employed sampling procedure led to the production of representative estimates at the national, regional, provincial level.