Sample Design for Applying the Survey in Wobulenzi

The stratified sampling plan was designed as part of the preparation for the survey. The households in Wobulenzi Town Council were stratified into two strata; namely Stratum I for Core Urban (Wobulenzi East, Wobulenzi West, Zones Luzzi and Katale of Wobulenzi Central); and Stratum II (Katikamu, Bukalasa and zones Kikoma and Kikasa of Wobulenzi Central) for those households in Peri-Urban. A representative sample was drawn from each of the stratum. . All households in the strata were treated the same way (no divide between connected and not connected), since those not connected fetch water from those connected. It is assumed that the two categories (connected and not connected) may have similar issues related to governance and social accountability.

The application of a petinent formula for this context suggested a sample size of 316 households per stratum, thereby giving a total of 632 households for both strata. Each stratum formed a population to facilitate the selection of the survey units. The sample size proposed enabled generation of representative information on all core variables that were included in the survey. However, given that the proposed sample size per stratum was over 5% of the stratum population, a finite population correction factor was applied. The finite population correction factor measures how much extra precision we achieve when the sample size become close to the population size. Seven (7) zones/villages were randomly selected in each of the stratum. The sample for each of the seven (7) zones/ villages per stratum was selected with probability proportional to size (PPS). In each of the selected zone for Stratum I, 33 households were randomly selected; while in Stratum II, 36 households.

Selection of households for Interview
A household is defined as a group of people who normally live and eat together. Very often the household will be a family living in the same house or compound and eating together, although in some instances a household may be different from a family. A household will normally consist of a head (male or female), a spouse, children and sometimes relatives and visitors.

If two or more people, each with his own separate housekeeping arrangements, live in the same dwelling, they should be treated as separate households. If a man has two or more wives and they with their children live and eat together, they form one household. If each wife and her children live and eat separately, then this family will form more than one household. A household may consist of one person who eats and lives on his/ her own or it may consist of several persons who are not related to each other. What matters is that they live in the same household or compound and eat together.

To facilitate the selection of units for interview, a comprehensive listing of households was undertaken. The purpose of the household listing was to obtain a comprehensive updated list of all households in the village without any omission or duplication and then to randomly (without bias) select a sample of households, for interview.