The 2005 Guyana HIV/AIDS Indicator Survey (GAIS) is the first household-based, comprehensive survey on HIV/AIDS to be carried out in Guyana. The 2005 GAIS was implemented by the Guyana Responsible Parenthood Association (GRPA) for the Ministry of Health (MoH). ORC Macro of Calverton, Maryland provided technical assistance to the project through its contract with the U.S. Agency for International Development (USAID) under the MEASURE DHS program. Funding to cover technical assistance by ORC Macro and for local costs was provided in their entirety by USAID/Washington and USAID/Guyana.
The 2005 GAIS is a nationally representative sample survey of women and men age 15-49 initiated by MoH with the purpose of obtaining national baseline data for indicators on knowledge/awareness, attitudes, and behavior regarding HIV/AIDS. The survey data can be effectively used to calculate valuable indicators of the President’s Emergency Plan for AIDS Relief (PEPFAR), the Joint United Nations Program on HIV/AIDS (UNAIDS), the United Nations General Assembly Special Session (UNGASS), the United Nations Children Fund (UNICEF) Orphan and Vulnerable Children unit (OVC), and the World Health Organization (WHO), among others. The overall goal of the survey was to provide program managers and policymakers involved in HIV/AIDS programs with information needed to monitor and evaluate existing programs; and to effectively plan and implement future interventions, including resource mobilization and allocation, for combating the HIV/AIDS epidemic in Guyana.
Other objectives of the 2005 GAIS include the support of dissemination and utilization of the results in planning, managing and improving family planning and health services in the country; and enhancing the survey capabilities of the institutions involved in order to facilitate the implementation of surveys of this type in the future.
The 2005 GAIS sampled over 3,000 households and completed interviews with 2,425 eligible women and 1,875 eligible men. In addition to the data on HIV/AIDS indicators, data on the characteristics of households and its members, malaria, infant and child mortality, tuberculosis, fertility, and family planning were also collected.
Kind of data
Sample survey data [ssd]
- v01: Edited, anonymous dataset for public distribution.
Unit of analysis
Producers and sponsors
Guyana Responsible Parenthood Association
Ministry of Health
U.S. Agency for International Development
Financial and technical support
MEASURE DHS program
Financial and technical support
Bureau of Statistics
Pan American Health Organization
The primary objective of the 2005 GAIS is to provide estimates with acceptable precision for important population characteristics such as HIV/AIDS related knowledge, attitudes, and behavior. The population to be covered by the 2005 GAIS was defined as the universe of all women and men age 15-49 in Guyana.
The major domains to be distinguished in the tabulation of important characteristics for the eligible population are:
• Guyana as a whole
• The urban area and the rural area each as a separate major domain
• Georgetown and the remainder urban areas.
Administratively, Guyana is divided into 10 major regions. For census purposes, each region is further subdivided in enumeration districts (EDs). Each ED is classified as either urban or rural. There is a list of EDs that contains the number of households and population for each ED from the 2002 census. The list of EDs is grouped by administrative units as townships. The available demarcated cartographic material for each ED from the last census makes an adequate sample frame for the 2005 GAIS.
The sampling design had two stages with enumeration districts (EDs) as the primary sampling units (PSUs) and households as the secondary sampling units (SSUs). The standard design for the GAIS called for the selection of 120 EDs. Twenty-five households were selected by systematic random sampling from a full list of households from each of the selected enumeration districts for a total of 3,000 households. All women and men 15-49 years of age in the sample households were eligible to be interviewed with the individual questionnaire.
The database for the recently completed 2002 Census was used as a sampling frame to select the sampling units. In the census frame, EDs are grouped by urban-rural location within the ten administrative regions and they are also ordered in each administrative unit in serpentine fashion. Therefore, this stratification and ordering will be also reflected in the 2005 GAIS sample.
Based on response rates from other surveys in Guyana, around 3,000 interviews of women and somewhat fewer of men expected to be completed in the 3,000 households selected.
Several allocation schemes were considered for the sample of clusters for each urban-rural domain. One option was to allocate clusters to urban and rural areas proportionally to the population in the area. According to the census, the urban population represents only 29 percent of the population of the country. In this case, around 35 clusters out of the 120 would have been allocated to the urban area. Options to obtain the best allocation by region were also examined. It should be emphasized that optimality is not guaranteed at the regional level but the power for analysis is increased in the urban area of Georgetown by departing from proportionality. Upon further analysis of the different options, the selection of an equal number of clusters in each major domain (60 urban and 60 rural) was recommended for the 2005 GAIS. As a result of the nonproportionalallocation of the number of EDs for the urban-rural and regional domains, the household sample for the 2005 GAIS is not a self-weighted sample.
The 2005 GAIS sample of households was selected using a stratified two-stage cluster design consisting of 120 clusters. The first stage-units (primary sampling units or PSUs) are the enumeration areas used for the 2002 Population and Housing Census. The number of EDs (clusters) in each domain area was calculated dividing its total allocated number of households by the sample take (25 households for selection per ED). In each major domain, clusters are selected systematically with probability proportional to size.
The sampling procedures are more fully described in "Guyana HIV/AIDS Indicator Survey 2005 - Final Report" pp.135-138.
• From a total of 3,055 households in the sample, 2,800 were occupied. Among these households, interviews were completed in 2,608, for a response rate of 93 percent.
• A total of 2,776 eligible women were identified and interviews were completed with 2,425 of these women, yielding a response rate of 87 percent.
• Out of 2,441 eligible men identified in the 3,055 households in the sample, only 1,875 were successfully interviewed, yielding a response rate of 77 percent.
• All the response rates are lower for the urban sample than they are for the rural, particularly for men (69 percent in Georgetown urban).
• The primary reason for non-response among both eligible men and women was the failure to find individuals at home despite repeated visits to the household. The substantially lower response rate for men reflects the more frequent and longer absences of men from the household, principally related to their employment and lifestyle.
Since the 2005 GAIS sample is unbalanced among region areas, it requires a final weighting adjustment procedure to provide estimates for the entire country.
For the i-th cluster in a given area combination (location by residence), if “c” is the fixed number of households selected out of the total households (Li) found in the 2005 listing process, then the household probability in the selected i-th cluster can be expressed as
P2i = ( c / Li )
The final households overall probability in the i-th cluster could be calculated as
fi = P1i * P2i
and the sampling design weight for the i-th cluster is given as
1/ fi = 1 / ( P1i * P2i )
Dates of collection
Mode of data collection
Two types of questionnaires were used in the survey, namely: the Household Questionnaire and the Individual Questionnaire. The contents of these questionnaires were based on model questionnaires developed by the MEASURE DHS program. In consultation with USAID/Guyana, MoH, GRPA, and other government agencies and local organizations, the model questionnaires were modified to reflect issues relevant to HIV/AIDS in Guyana. The questionnaires were finalized around mid-May.
The Household Questionnaire was used to list all the usual members and visitors in the selected households. For each person listed, information was collected on sex, age, education, and relationship to the head of the household. An important purpose of the Household Questionnaire was to identify women and men who were eligible for the individual interview.
The Household Questionnaire also collected non-income proxy indicators about the household's dwelling unit, such as the source of water; type of toilet facilities; materials used for the floor, roof and walls of the house; and ownership of various durable goods and land. As part of the Malaria Module, questions were included on ownership and use of mosquito bednets.
The Individual Questionnaire was used to collect information from women and men age 15-49 years and covered the following topics:
• Background characteristics (age, education, media exposure, employment, etc.)
• Reproductive history (number of births and—for women—a birth history, birth registration, current pregnancy, and current family planning use)
• Marriage and sexual activity
• Husband’s background
• Knowledge about HIV/AIDS and exposure to specific HIV-related mass media programs
• Attitudes toward people living with HIV/AIDS
• Knowledge and experience with HIV testing
• Knowledge and symptoms of other sexually transmitted infections (STIs)
• The malaria module and questions on tuberculosis
Ministry of Health
The processing of the GAIS questionnaires began in mid-July 2005, shortly after the beginning of fieldwork and during the first visit of the ORC Macro data processing specialist. Questionnaires for completed clusters (enumeration districts) were periodically submitted to GRPA offices in Georgetown, where they were edited by data processing personnel who had been trained specifically for this task. The concurrent processing of the data—standard for surveys participating in the DHS program—allowed GRPA to produce field-check tables to monitor response rates and other variables, and advise field teams of any problems that were detected during data entry. All data were entered twice, allowing 100 percent verification. Data processing, including data entry, data editing, and tabulations, was done using CSPro, a program developed by ORC Macro, the U.S. Bureau of Census, and SERPRO for processing surveys and censuses. The data entry and editing of the questionnaires was completed during a second visit by the ORC Macro specialist in mid-September. At this time, a clean data set was produced and basic tables with the basic HIV/AIDS indicators were run. The tables included in the current report were completed by the end of November 2005.
Sampling errors can be evaluated statistically. The sample of respondents selected in the 2005 GAIS is only one of many samples that could have been selected from the same population, using the same design and expected size. Each of these samples would yield results that differ somewhat from the results of the actual sample selected. Sampling errors are a measure of the variability between all possible samples. Although the degree of variability is not known exactly, it can be estimated from the survey results.
A sampling error is usually measured in terms of the standard error for a particular statistic (mean, percentage, etc.), which is the square root of the variance. The standard error can be used to calculate confidence intervals within which the true value for the population can reasonably be assumed to fall. For example, for any given statistic calculated from a sample survey, the value of that statistic will fall within a range of plus or minus two times the standard error of that statistic in 95 percent of all possible samples of identical size and design.
If the sample of respondents had been selected as a simple random sample, it would have been possible to use straightforward formulas for calculating sampling errors. However, the 2005 GAIS sample is the result of a multi-stage stratified design, and, consequently, it was necessary to use a more complex formula. The computer software used to calculate sampling errors for the 2005 GAIS is the sampling error module in ISSA (Integrated System for Survey Analysis). This module uses the Taylor linearization method of variance estimation for survey estimates that are means or proportions. Another approach, the Jackknife repeated replication method is used for variance estimation of more complex statistics such as fertility and mortality rates.
The Taylor linearization method treats any percentage or average as a ratio estimate, r = y/x, where y represents the total sample value for variable y, and x represents the total number of cases in the group or subgroup under consideration.
Sampling errors for the 2005 GAIS are calculated for selected variable s considered to be of primary interest for the women’s and men’s samples. The sampling errors for mortality rates are presented for the ten-year period preceding the survey. The DEFT is considered undefined when the standard error considering simple random sample is zero (when the estimate is close to 0 or 1). In the case of the total fertility rate, the number of unweighted cases is not relevant, as there is no known unweighted value for woman-years of exposure to childbearing.
The confidence interval (e.g., as calculated for children ever born to women aged 40-49) can be interpreted as follows: the overall average from the national sample is 6.104 and its standard error is 0.078. Therefore, to obtain the 95 percent confidence limits, one adds and subtracts twice the standard error to the sample estimate (i.e., 6.104 ± 2×0.078). There is a high probability (95 percent) that the true average number of children ever born to all women aged 40 to 49 is between 5.948 and 6.261.
The sampling errors are more fully described in appendix B in document "Guyana HIV/AIDS Indicator Survey 2005 - Final Report" pp.139-148.
Other forms of data appraisal
A series of data quality tables are available to review the quality of the data and include the following:
- Household age distribution
- Age distribution of eligible and interviewed women
- Age distribution of eligible and interviewed men
- Completeness of reporting
- Births by calendar year
- Reporting of age at death in days
- Reporting of age at death in months
The results of each of these data quality tables are shown in appendix C in document "Guyana HIV/AIDS Indicator Survey 2005 - Final Report" pp.149-153.
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
Guyana Responsible Parenthood Association, Ministry of Health. Guyana HIV/AIDS Indicator Survey 2005. Ref. GUY_2005_AIS_v01_M. Dataset downloaded from www.measuredhs.com 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.