Multiple Indicator Cluster Survey 2011 - Roma Settlements
Istrazivanje visestrukih pokazatelja 2010
Bosnia and Herzegovina
The 2011–2012 Multiple Indicator Cluster Survey (MICS) on Roma in BiH was conducted by the Ministry for Human Rights and Refugees of BiH (MHRR BiH) in cooperation with the Agency for Statistics of BiH (BHAS). Financial and technical support was provided by UNICEF, with additional financial support being provided by UNFPA and the UNHCR. The survey was undertaken as part of the fourth global round of MICS (MICS4).
The survey is based on a representative sample of 1,791 households, with a response rate of 86 percent. In these households, 1,380 women and 1,456 men aged 15-49 were interviewed and questionnaires completed for 748 children under age five.
Kind of data
Sample survey data [ssd]
- v01: Edited, anonymous datasets for public distribution.
Unit of analysis
The survey covered household members in Roma settlements, all women aged between 15-49 years, all children under 5 living in the household, and all men aged 15-49 years.
Producers and sponsors
United Nations Children’s Fund
Ministry for Human Rights and Refugees of Bosnia and Herzegovina
Agency for Statistics of Bosnia and Herzegovina
United Nations Children’s Fund
Financial and technical support
United Nations Population Fund
United Nations High Commissioner for Refugees
The primary objective of the sample design for the MICS survey on Roma in BiH was to produce statistically reliable estimates for most indicators at the BiH, FBiH and RS level.
A one-stage stratified sampling approach was used for the selection of the survey sample.
The target sample size for the Roma communities MICS was calculated as 1,800 households in 62 municipalities. Data from MICS3 on Roma in Serbia in 2005 was used to calculate specific indicators. At the time of the sample design the Serbian MICS3 was the only unique source of data on the Roma population in the sub-region (BiH, Montenegro, Croatia, the Former Yugoslav Republic of Macedonia and Serbia). The key indicator used for the calculation of the sample size was the immunisation coverage rate for the tuberculosis vaccine amongst children aged 18-29 months. Out of the 30 indicators 17 required a smaller sample size than 1,800 households and the remaining 13 required a larger sample size of households. Of the 13 indicators that required a larger sample size than that of 1,800 households the average size of the confidence interval for a sample of 1,800 households was calculated at 7.4 percent.
Sampling frames for the Roma population were non-existent in BiH until 2009 when MHRR BiH conducted an enumeration of Roma in BiH as part of activities within the Decade of Roma Inclusion 2005-2015.
The master sample frame was prepared using information from the 2009 enumeration. During the 2009 enumeration procedure data was collected on 4,307 Roma households living in Roma communities in 67 municipalities. The total number of municipalities in BiH is 142. Data from the remaining 75 municipalities was not collected due to a lack of information on the presence of Roma in these municipalities. Five municipalities with 1 Roma household were excluded from the master sample frame.
Municipalities in the FBiH, RS and BD were identified as the sample strata and a one-stage stratified sampling approach was used for the selection of the survey sample, with households defined as the primary sampling units (PSUs).
Households were selected from each of the sampling strata (municipalities) by using systematic pps sampling procedures, based on the estimated sizes of the strata from the 2009 enumeration of Roma in BiH.
All households where the head of household declared himself or herself to be of Roma ethnicity were considered as Roma households.
Households were selected within each stratum based on the date of birth of the household head. If the date of birth of the household head was not available then the date of birth of the next oldest person in the household with an available date of birth was used. If none of the household members had an available date of birth then the date of birth of the interviewer was used as the reference.
The sampling procedures are more fully described in "Bosnia and Herzegovina Multiple Indicator Cluster Survey (MICS) 2011 - Roma Settlements - Final Report" pp.144-147.
Of the 1,791 households selected for the sample 1,788 were found to be occupied. Of these, 1,544 households were successfully interviewed for a household response rate of 86 percent. In the interviewed households 1,457 women aged 15-49 were identified of which 1,380 were successfully interviewed, yielding a response rate of 95 percent. In addition, 1,559 men aged 15-49 were listed in the household questionnaire. Questionnaires were completed for 1,456 eligible men, which corresponds to a response rate of 93 percent. There were 760 children under age five listed in the household questionnaire and questionnaires were completed for 748 children, which corresponds to a response rate of 98 percent. The overall response rates for the women’s, men’s and children’s questionnaires were 82 percent, 81 percent and 85 percent respectively.
The Roma Multiple Indicator Cluster Survey in BiH sample was not self-weighting. In order to obtain representative results for the Roma settlements, sample weights were calculated. These sample weights were used in the subsequent analyses of the survey data. In the calculation of the weights the initial number of households by municipality (from the 2009 enumeration of Roma) was replaced by updated data collected during the fieldwork listing.
Since the original sample allocation was based on the 2009 sampling frame, there were cases where the number of households selected in the municipality was greater than N’h, in which case a value of 1 was used for the first stage probability of selection instead of the formula.
A second component in the calculation of sample weights accounted for the level of non-response for the households and individuals interviews. The adjustment for household non-response is equal to the inverse value of:
RRh = Number of interviewed households in stratum h/ Number of occupied households listed in stratum h
After completion of the fieldwork the response rates were calculated for each sampling stratum. These were used to adjust the sample weights calculated for each cluster.
The non-response adjustment factors for women’s, men’s and under-5’s questionnaires were applied to the adjusted household weights. Numbers of eligible women and children under-5 were obtained from the roster of household members in the Household Questionnaire for households where interviews were completed.
The design weights for the households were calculated by multiplying the above factors for each enumeration area. These weights were then standardised (or normalised), one purpose of which was to make the weighted sum of the interviewed sample units equal to the total sample size at the national level.
Normalisation was achieved by dividing the full sample weights (adjusted for non-response) by the average of these weights across all households at the BiH level. This was performed by multiplying the sample weights by a constant factor equal to the unweighted number of households at the national level and divided by the weighted total number of households (using the full sample weights adjusted for non-response). A similar standardisation procedure was followed for obtaining standardised weights for the women’s, men’s and children under-5 questionnaires. Adjusted (normalised) weights varied between 0.483875 and 2.859160 in the 62 sample municipalities.
Sample weights were appended to all data sets and analyses were performed by weighting each household, woman, men or child under-5 with these sample weights.
Dates of collection
Mode of data collection
Data collection supervision
There is one supervisor for each of the 3 data collection teams in the field.
The questionnaires for the Generic MICS were structured questionnaires based on the MICS4 model questionnaire with some modifications and additions. Household questionnaires were administered in each household, which collected various information on household members including sex, age and relationship. The household questionnaire includes household listing form, education, water and sanitation, household characteristics, child discipline and hand washing.
In addition to a household questionnaire, questionnaires were administered in each household for women age 15-49, children under age five and men age 15-49. For children, the questionnaire was administered to the mother or primary caretaker of the child.
The women's questionnaire includes woman's background, access to mass media and ICT, child mortality, desire for last birth, maternal and newborn health, illness symptoms, contraception, unmet need, attitudes toward domestic violence, marriage/union, sexual behavior, HIV/AIDS, tobacco and alcohol use, life satisfaction and health care.
The children's questionnaire includes child's age, birth registration, early childhood development, breastfeeding, care of illness, immunisation and anthropometry.
The men's questionnaire includes man's background, access to mass media and ICT, child mortality, attitudes toward domestic violence, marriage/union, sexual behavior, HIV/AIDS, tobacco and alcohol use, life satisfaction and health care.
The questionnaires were based on the MICS4 model questionnaire. From the MICS4 model English version the questionnaires were translated into the local languages used in BiH. The questionnaires were pre-tested in the FBiH in three municipalities in Sarajevo Canton (Centar, Ilijas and Novo Sarajevo) during September 2011. The plan provided for 18 households to be interviewed (9 each in urban and rural areas). These households were selected using a random selection method based on the date of birth of the household head. On the basis of the pre-test results, modifications were then made to the wording and translation of the questionnaires for the survey.
Bosnia and Herzegovina Ministry for Human Rights and Refugees
Agency for Statistics of Bosnia and Herzegovina
The data was entered and processed by the MHRR BiH. The data was entered using CSPro software into four microcomputers by 4 trained data entry operators; the process was supervised by data entry supervisors and a data entry coordinator. Data entry began ten days after the start of data collection (20 November 2011) and was completed on 26 April 2012.
The SPSS (Statistical Package for Social Sciences) software programme (Version 18) was used to analyse the data and model syntax and tabulation plans developed by UNICEF were also used for this purpose. In order to ensure quality control all questionnaires were double entered and internal consistency checks were performed. Procedures and standard programmes developed under the global MICS4 programme and adapted to the questionnaires for the survey on Roma in BiH were used throughout.
The sample of respondents selected in the MICS survey on Roma in BiH was only one of the samples that could have been selected from the same population, using the same design and size. Each of these samples would have yielded results that differed somewhat from the results of the actual sample selected. Sampling errors are a measure of the variability between the estimates from all possible samples. The extent of variability is not known exactly but can be estimated statistically from the survey data.
The simple one-stage stratified sample design for the MICS survey on Roma in BiH is reflected in the calculations of the sampling errors, whereby the strata are municipalities and the primary sampling units (PSUs) are households (clusters of persons).
Given the overall high sampling rate (1,800/3,784), sampling without replacement was used in order to apply a finite population correction factor. As part of the estimation procedure, the first stage sampling rate for each stratum (municipality) was specified. For strata with a sampling rate of 1, the finite population correction factor was zero (resulting in a zero variance component for the corresponding stratum).
The sampling error measures below are presented in this appendix for each of the selected indicators.
- Standard error (se): Sampling errors are usually measured in terms of standard errors for particular indicators (means, proportions etc). Standard error is the square root of the variance of the estimate. The Taylor Linearization method was used for the estimation of standard errors.
- Coefficient of variation (se/r): is the ratio of the standard error to the value of the indicator and is a measure of the relative sampling error.
- Design effect (deff): is the ratio of the actual variance of an indicator, under the sampling method used in the survey, to the variance calculated under the assumption of simple random sampling. The square root of the design effect (deft) is used to show the efficiency of the sample design in relation to the precision. A deft value of 1.0 indicates that the sample design is as efficient as a simple random sample, while a deft value above 1.0 indicates an increase in the standard error due to the use of a more complex sample design.
- Confidence limits: are calculated to show the interval within which the true value for the population can be reasonably assumed to fall with a specified level of confidence. For any given statistic calculated from the survey the value of that statistic will fall within a range of plus or minus two times the standard error (r + 2.se or r – 2.se) of the statistic in 95 per cent of all possible samples of identical size and design.
The SPSS Version 18 Complex Samples Module was used for the calculation of sampling errors within the MICS data. Sampling errors were calculated for indicators of primary interest for the BiH, FBiH, RS and BD levels. Five of the selected indicators were based on household members, 19 were based on women, 10 were based on men and 17 were based on children under 5. All indicators presented here are in the form of proportions.
Other forms of data appraisal
A series of data quality tables are available to review the quality of the data and include the following:
- Age distribution of the household population
- Age distribution of eligible and interviewed women
- Age distribution of eligible and interviewed men
- Age distribution of children under 5 in household and children under 5 questionnaires
- Women’s completion rates by socio-economic characteristics of households
- Men’s completion rates by socio-economic characteristics of households
- Completion rates for under-5 questionnaires by socio-economic characteristics of households
- Completeness of reporting
- Completeness of information for anthropometric indicators
- Heaping in anthropometric measurements
- Observation of places for hand washing
- Observation of under-5’s birth certificates
- Observation of vaccination cards
- Selection of children age 2–14 years for the child discipline module
- School attendance by single age
- Sex ratio at birth amongst children ever born and living
- Number of household population by single age
The results of each of these data quality tables are shown in appendix D in document "Bosnia and Herzegovina Multiple Indicator Cluster Survey (MICS) 2011 - Roma Settlements - Final Report" pp.164-174.
Users of the data agree to keep confidential all data contained in these datasets and to make no attempt to identify, trace or contact any individual whose data is included in these datasets.
Use of the dataset must be acknowledged using a citation which would include:
- the Identification of the Primary Investigator
- the title of the survey (including country, acronym and year of implementation)
- the survey reference number
- the source and date of download.
Ministry for Human Rights and Refugees of Bosnia and Herzegovina, Agency for Statistics of Bosnia and Herzegovina and United Nations Children’s Fund. Bosnia and Herzegovina Multiple Indicator Cluster Survey (MICS) 2011 - Roma Settlements, Ref. BIH_2011_MICS-RS_v01_M. Dataset downloaded from [url] on [date].
Disclaimer and copyrights
The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
Ministry for Human Rights and Refugees of Bosnia and Herzegovina
Agency for Statistics of BiH
Federal Ministry of Health
Ministry of Health and Social Welfare of Republika Srpska
Institute for Public Health of the Federation of Bosnia and Herzegovina