Ghana - Ghana Demographic and Health Survey 2003, Round four

The sample for the 2003 GDHS covered the population residing in private households in the country. A representative probability sample of about 6,600 households was selected nationwide. The list of enumeration areas (EAs) from the 2000 Ghana Population and Housing Census was used as a frame for the sample.

The frame was first stratified into the 10 administrative regions in the country, then into rural and urban EAs. The sample was selected in such a manner as to allow for separate estimates for key indicators for the country as a whole, for each of the 10 regions in Ghana, as well as for urban and rural areas separately.

The 2003 GDHS used a two-stage stratified sample design.

At the first stage of sampling, 412 sample points or EAs were selected, each with probability proportional to size, based on the number of households. A complete household listing exercise was carried out between May and June 2003 within all the selected EAs (clusters).

The second stage of selection involved systematic sampling of households from this list. The sample selected per EA varied by region depending on the population size. Fifteen households per EA were selected in all the regions except in Brong Ahafo, Upper East, and Upper West regions, where 20 households per EA were selected, and in the Northern region, where 16 households per EA were selected.


There was no deviation


A total of 6,628 households were selected in the sample, of which 6,333 were occupied at the time of fieldwork. The difference between selected and occupied households is largely due to structures being vacant or destroyed. Successful interviews were conducted in 6,251 households, yielding a response rate of 99 percent.

In the households interviewed in the survey, a total of 5,949 eligible women age 15-49 were identified; interviews were completed with 5,691 of these women, yielding a response rate of 96 percent. In the same households, a total of 5,345 eligible men age 15-59 were identified and interviews were completed with 5,015 of these men, yielding a male response rate of 94 percent. The response rates are slightly lower for the urban than rural sample and among men than women. The principal reason for non-response among both eligible women and men was the failure to find individuals at home despite repeated visits to the household. The lower response rate for men reflects the more frequent and longer absences of men from the household, principally related to their employment and life style.

Response rates for the HIV testing component were lower than those for the interviews. In fact, the
coverage rate for testing among women is consistent across all age groups (88 to 91 percent). Response
rates are somewhat have more variations by age among men (77 to 83 percent).


The variable Sample weight was used to weight the data