Survey ID Number
Multiple Indicator Cluster Survey 2010
The primary objective of the sample design was to produce statistically reliable estimates of most indicators, at the national level, and for 4 regions: Belgrade, Vojvodina, Sumadija and Western Serbia and Southern and Eastern Serbia, for urban and rural areas, of the country.
A stratified, two-stage random sampling approach was used for the selection of the survey sample.
The target sample size for the Serbia MICS4 was calculated as 6,800 households and 400 enumeration areas, considering the proposed formula and budget available. For the calculation of the sample size, the key indicator used was the percentage of children aged 0-4 years who had had Acute Respiratory infections.
The resulting number of households from this exercise was about 23,000 households, which is the sample size needed to provide a large number of children under 5 (about 3,500) for drawing reliable conclusions. Therefore, in order to reduce the number of households in the sample, but not to lose estimation reliability, the stratification of the sample into categories with and without children aged 0-4 years was needed. The required number of households in each category was obtained supposing an overall sample of 6,800 households, 400 clusters and same number of households with children under 5 per cluster. Assuming one child under 5 per household and considering the required number of sample children, the total sample size was calculated as 3,600 (9 per cluster) households with children under 5 and 3,200 (8 per cluster) of households without children under 5. Thus, the overall number of households to be selected per cluster was determined as 17 households. The final target number of sample households with children per cluster was increased to 10 (12 for Belgrade region) in order to compensate for sample clusters with less households with children found in the listing.
Stratification of enumeration areas for Serbia was done according to type of settlement (urban and rural), and 25 Areas (Belgrade, West Backa, South Banat, South Backa, North Banat, North Backa, Central Banat, Srem, Zlatibor,Kolubara, Macva, Moravica, Pomoravlje, Rasina, Raška, Šumadija, Bor, Branicevo, Zajecar, Jablanica, Nišava, Pirot, Danube, Pcinja, and Toplica).
A proportional allocation of the sample based on the number of households in the urban and rural domains of the 25 Areas was slightly adjusted. At the level of Serbia, the number of enumeration areas for the rural domain was reduced by 10 enumeration areas and allocated to the urban domain, where the non-response rate was expected to be higher (about 20%). The table below shows the allocation of clusters to the sampling strata.
The sampling procedures are more fully described in "Multiple Indicator Cluster Survey 2010 - Final Report" pp.257-260.