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 prodvide 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 additon, the sample was designed to provide estimates for each of the 11 regions for key indicators.  Georgia is devided into 11 regions: Tbilisi, Kakheti, Mtskheta - Mtianeti, Shida Kartli, Kvemo Kartli, Samtskhe - Javakheti, Racha - Lechkhumi and Kvemo, Svaneti, Imereti, Guria, Samegrelo and Zemo Svaneti, Adjara.  The sample frame for this survey was based on the list of enumeration areas developed from the 2002 population census.

The primary sampling unit (PSU), the cluster for the 2005 MICS, is defined on the basis of the enumeration areas from the census frame.  The minimum PSU size in Georgia is 11 households and the maximum PSU size is 188 households. The average PSU size is 70.8 households. While constructing the sampling frame the PSUs that are smaller then 30 households is merged with the neighbouring PSUs to achieve the minimum size of PSU equalling to 30 households. Although the original sample design for the Georgia MICS 2005 called for approximately 14000 households with an equal number of clusters (42) of households in each of the 11 regions, stratified into urban and rural areas, this sample design was changed to use a more complicated stratification design, with unequal numbers of clusters in each stratum.  The rationale for this was for the selection to more closely follow the population distribution of the population.  

The sample was selected in four stages and in the first two stages, sample design was stratified according to 11 regions, 3 settlement types (Large town, Small town, and Village), and 4 geographic strata (Valley, Foothills, Mountain, and High mountain). This stratification was applied in all regions, except the city of Tbilisi where the region is stratified according to 10 districts. In total 49 separate strata were identified. The last two stages of the sample design were for the selection of clusters and households.

First stage of sampling:  The number of clusters based on sample size calculations was 467 and these were allocated to regions based on the cube root of the number of households in the region.  Because the number of clusters for the Racha-Lechkumi region was small (12 clusters), it was decided to increase the number of clusters in that region by 8 for a total of 20 clusters in that region for a total of 475 clusters nationwide.

Second stage of sampling: Within each region, another level of stratification was on a combination of the following: size of settlement (large town, small town, and village) and topography (valley, foothills, mountain, and mountain).  The allocation of the number of clusters for a settlement/topography stratum was based on the square root of the number of households in each stratum.  Some regions did not have each of the different size settlements or topography.  Also, in Tbilisi, the Rayons (districts) were used for stratification.

Third stage of sampling: Within each stratum, clusters were selected with probability proportional to population size (PPS).

Fourth stage of sampling:  Within each cluster, 30 households were systematically selected, resulting with 14,250 households.

The Georgia Multiple Indicator Cluster Survey sample is not self-weighted. The basic weighting of the data has been done using the inverse of the probability of selection of each household.

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 interviewd.

No replacement of households was permitted in case of non-response or non-contactable households.  Adjustments were made to the sampling weights to correct for non-response, according to MICS standard procedures.

The sampling procedures are more fully described in the sampling design document and the sampling appendix of the final report.

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 14,250 households selected for the sample, 12,268 were found to be occupied.  Of these, 12,010 were successfully interviewed for a household response rate of 97.9 percent.  In the interviewed households, 10,908 women (age 15-49) were identified.  Of these, 9,847 were successfully interviewed, yielding a response rate of 90.3 percent.  In addition, 2,196 children under age five were listed in the household questionnaire.  Questionnaires were completed for 2,037 of these children, which corresponds to a response rate of 92.8 percent.  Overall response rates of 88.4 and 90.8 are calculated for the women's and under-5's interviews respectively.

Response rates were similar across residence while slight variations in response rates observed by regions.  Although the capital city of Tbilisi had the lowest household response rate, the highest response rate for the women questionnaire was found in Tbilisi.  The highest response rates for household and children under-5 questionnaires were found in Racha-Lechkhumi and Kvemo Svaneti while Guria region had the lowest response rate for children under-5 questionnaire.

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: APR-26-2009 using the IHSN Microdata Management Toolkit