The sample for the 2004-05 UHSBS covered the population residing in households in the country. A representative probability sample of 10,425 households was selected for the UHSBS, and an additional 12 households were found during field work for a total of 10,437. The sample was constructed to allow for separate estimates for key indicators for each of nine regions created for the survey, consisting of eight groups of the (then) 56 districts in Uganda, and Kampala, the capital, as a region on its own. The regions were delineated as follows:
1 Central: Kalangala, Kiboga, Luwero, Masaka, Mpigi, Mubende, Nakasongola, Rakai, Sembabule, and Wakiso
3 East Central: Bugiri, Iganga, Jinja, Kamuli, Kayunga, Mayuge, and Mukono
4 Eastern: Busia, Kapchorwa, Mbale, Pallisa, Sironko, and Tororo
5 Northeast: Kaberamaido, Katakwi, Kotido, Kumi, Moroto, Nakapiripirit, and Soroti
6 North Central: Apac, Gulu, Kitgum, Lira, and Pader
7 West Nile: Adjumani, Arua, Moyo, Nebbi, and Yumbe
8 Western: Bundibugyo, Hoima, Kabarole, Kamwenge, Kasese, Kibaale, Kyenjojo, and Masindi
9 Southwest: Bushenyi, Kabale, Kanungu, Kisoro, Mbarara, Ntungamo, and Rukungiri.
The sample was allocated roughly equally across all nine regions to allow a sufficient size in each to produce reliable results. Since the sample was not allocated in proportion to the size of each region, the UHSBS sample is not self-weighting at the national level. Consequently, weighting factors have been applied to the data to produce nationally representative results.
The survey utilised a two-stage sample design. The first stage involved selecting sample points or clusters from a list of enumeration areas (EAs) covered in the 2002 Population Census. A total of 417 clusters composed of 74 urban and 343 rural points were selected. The second stage of selection involved the systematic sampling of households from the census list of households in each cluster. Twenty-five households were selected in each EA.
All women and men aged 15-59 who were either permanent residents of the households in the sample or visitors present in the household on the night before the survey were eligible to be interviewed in the survey. Unlike most studies in which the age category reflects the reproductive age group 15-49, the upper age cutoff in this survey was extended to 59 years so as to include the segment of the population that remains sexually active up to that age. Nevertheless, since most of the internationally accepted HIV/AIDS indicators are based on the population aged 15-49, most of the results presented in this report reflect this age group.
All women and men who were interviewed were asked to voluntarily give a blood sample for testing. Blood samples were also drawn from children under age five years after obtaining consent from their parents or caretakers. Children aged 5-14 years were not enrolled in the survey because other studies have shown a very low HIV prevalence in this age group.