Sampling

Sampling Procedure

The principal objective of the sample design was to provide current and reliable estimates on a set of indicators covering the four major areas of the World Fit for Children declaration, including promoting healthy lives; providing quality education; protecting against abuse, exploitation and violence; and combating HIV/AIDS.  The population covered by the 2005 MICS is defined as the universe of all women aged 15-49 and all children aged under 5.  A sample of households was selected and all women aged 15-49 identified as usual residents of these households were interviewed.  In addition, the mother or the caretaker of all children aged under 5 who were usual residents of the household were also interviewed about the child.

The 2005 MICS collected data from a nationally representative sample of households, women and children.  The primary focus of the 2005 MICS was to provide estimates of key population and health, education, child protection and HIV related indicators for the country as a whole, and for urban and rural areas separately.  In addition, the sample was designed to provide estimates for each of the 7 regions for key indicators.  Belarus is divided into 7 regions.  Each region is subdivided into big cities, small towns and rural areas (selskie sovety).  In addition each unit was subdivided into polling stations in urban areas and rural settlements in selskie sovety.  In total Belarus includes 20 big cities, 187 small cities and 1388 selskie soveties.  

MICS3 is utilizing the sample frame of household surveys that is being used in the republic. To provide uniform distribution of the sample allocation of the households in the republic the selection was carried out in Brest, Vitebsk, Gomel, Grodno, Minsk, Mogilev regions and in Minsk city.

Three stage sampling has been carried out.  At the first stage in each of the regions (oblasts) three sampling strata has been created: big cities, small towns and rural areas (selskie sovety); at the second stage - polling stations in urban areas and rural settlements in selskie sovety; at the third stage in the selected settlements the households were selected.

Within the strata of big cities, at first stage, 20 big cities were selected with the probability equalling to 1.

Within the strata of small towns 29 small towns were sampled systematically with pps and the measure of size was total population of the small towns. The number of small towns in every region (oblast) was selected based on division of the total number of population of all small towns of each region into average household size (2,6), sample share (1/600) and  average load of interviewer (40). 

Within the strata of rural settlements (selskie sovety) at the first stage of sampling 53 rural settlements were selected systematically with pps and the measure of size was number of households in the rural settlement.

On the second stage of sampling within the big cities and the small towns the polling stations were selected as sampling unit, in the rural settlements - settlements in rural area (selskie sovety).

To cover the whole territory of the selected city the cartographical materials were used on the second stage of sampling within the big cities. The number of the polling stations was calculated based on division of the population of the city into the average size of the family (2,6), sample share (1/600) and  estimated number of the households in each polling station (20). 

Three polling stations were selected in each small town from the list of the polling stations, ranking by number of voters. 
In rural areas, taking into account the difficulty of access and scattered nature of settlements, the territories of the rural areas (selskie sovety) were divided into zones and the closest rural settlements were grouped. One zone was selected in each rural area (selskie sovety) and within this zone all settlements were investigated. 

Throughout the Republic of Belarus there were 304 polling stations and the rural zones in selskie sovery selected in 2005.

On the third stage of sampling, households were selected from the updated lists systematically taking into account the size of the cluster.  In big cities the size of the cluster which is selected from the updated list households within the territory of polling station is 19-20 households, in small towns the size of the cluster is 13-14 households, and in rural areas the size of the cluster is 39-40 households. The size of clusters is not uniform. Variation in cluster sizes for urban and rural settlements was done on purpose since existing sampling plan was considering load of one interviewer, as one of the parameters, and distribution of sampled population into the sampling domains - proportionally to the distribution in general population. 

Besides, taking into account the limited representation of children under 5 in the household sample, the additional sub-sample of households with children aged 0-4 was formed.  For this purpose, in each of the 304 clusters the lists of households was updated with the information on households with under 5 children through local out-patient health institutions. From these lists with higher probability then for households without children, the households with children aged 0-4 were selected. 

The resulting number of households for MICS3 sample in the Republic of Belarus was 7,000, including 2,857 households with children aged 0-4.

Following standard MICS data collection rules, if a household was actually more than one household when visited, then a) if the selected household contained two households, both were interviewed, or b) if the selected household contained 3 or more households, then only the household of the person named as the head was interviewed.

Deviation from Sample Design

No major deviations from the original sample design were made.  All sample enumeration areas were accessed and successfully interviewed with good response rates.

Response Rates

Of the 7,000 households selected for the sample, 100% were found to be occupied. Of these, 6,707 were successfully interviewed for a household response rate of 95.8% percent. In the interviewed households, 5,906 women (age 15-49) were identified. Of these, 5,895 were successfully interviewed, yielding a response rate of 99.8 percent. In addition, 3,051 children under age five were listed in the household questionnaire. Of these, questionnaires were completed for 3,051 which corresponds to a response rate of 100 percent. Overall response rates of 95.6% and 95.8% are calculated for the women's and under-5's interviews respectively.

Differentials in household response rates by regions were from 94.4 % in Mogilev region to 96.7% in Gomel region.

Weighting

Sample weights were calculated for each of the datafiles.  

Sample weights for the household data were computed as the inverse of the probability of selection of the household, computed at the sampling domain level (urban/rural within each region).  The household weights were adjusted for non-response at the domain level, and were then normalized by a constant factor so that the total weighted number of households equals the total unweighted number of households.  The household weight variable is called HHWEIGHT and is used with the HH data and the HL data.

Sample weights for the women's data used the un-normalized household weights, adjusted for non-response for the women's questionnaire, and were then normalized by a constant factor so that the total weighted number of women's cases equals the total unweighted number of women's cases.

Sample weights for the children's data followed the same approach as the women's and used the un-normalized household weights, adjusted for non-response for the children's questionnaire, and were then normalized by a constant factor so that the total weighted number of children's cases equals the total unweighted number of children's cases.
Generated: MAR-03-2008 using the IHSN Microdata Management Toolkit