Sample characteristics: South Africa
| Census/survey characteristics | |
| Type | Census |
| Title | Population Census, 1996 |
| Statistical agency | Statistics South Africa |
| Population universe | Every person present in South Africa on Census Night, October 9-10, 1996, should have been enumerated. |
| De jure or de facto | De facto |
| Census/survey day | October 10, 1996 |
| Field work period | October 10 to October 30, 1996 although, in some situations, it was necessary to continue enumeration through to December to ensure that as many people as possible were included. |
| Questionnaire | There were five different questionnaires that were used: 1) A household questionnaire which was completed in each household in the country. This questionnaire included information on each individual in the household, for example age and gender, as well as on the household as a whole, for example access to electricity and tap water. 2) An individual questionnaire, which was completed by individuals living on their own, for example those living in hostels or compounds. 3) A summary questionnaire for hostels. 4) A questionnaire for institutions, for example prisons, tourist hotels or homes for the aged. 5) A questionnaire for the homeless. |
| Type of fieldwork | Respondents were given the choice of being interviewed or of completing the questionnaire themselves. The vast majority of people chose to be interviewed.
A general enumerator was a temporary Stats SA staff member appointed to collect information about people who were living in households in private accommodation, for example, a house, a flat in a block of flats, a shack or a traditional dwelling, on census night. A special enumerator was appointed to enumerate people in special dwellings (institutions) such as hostels, prisons, hotels and hospitals. Special enumerators also collected information on the homeless or those living on the streets without shelter or in the open. |
| Estimated undercount | 10.7% |
| Microdata sample characteristics | |
| Sample design | The household was basically drawn as a 10% systematic sample of households from the census household file, stratified as specified below. The 10% person level sample was obtained by including all persons in these households plus the persons drawn in independent 10% systematic samples of all persons in special institutions and hostels.
NOTE: 19 districts in the Eastern Cape province are not organized into households, because of an error in the original data file. 1.3% of the sample is affected. |
| Sample fraction | 10% |
| Sample size (person records) | 3621164 |
| Sample weights | Computed by census agency and should be used for most types of analysis. The weight variable is the adjustment factor for undercount (for households or persons as appropriate) multiplied by 10 to inflate the 10% sample to the population. |
| Units identified in microdata | |
| Dwellings | No |
| Vacant units | No |
| Households | Yes |
| Collective dwellings | Yes |
| Smallest geography | Magisterial districts with 20,000+ population in 2001 |
| Unit definitions | |
| Dwellings | An occupied dwelling was a premises (visiting point or physical address) that was inhabited by one or more households on census night. An occupied dwelling may have been a house, room, flat or apartment, shack, hut, tent, caravan, houseboat, shop, school, etc. |
| Households | A household consists of a person, or a group of persons, who occupy a common dwelling (or part of it) for at least four days a week and who provide themselves jointly with food and other essentials for living. In other words, they live together as a unit. People who occupy the same dwelling, but who do not share food or other essentials, were enumerated as separate households. For example, people who shared a dwelling, but who bought food and ate separately, were counted as separate households. |
| Collective dwellings | A special dwelling is one which is not privately occupied by a household. It is usually an institution such as a prison, hotel, hostel, home for the aged, etc. Also hostels: a collective form of accommodation specifically built during the apartheid era for mine, factory, power station, municipal or other employees. |
| Census/survey characteristics | |
| Type | Census |
| Title | Census 2001 |
| Statistical agency | Statistics South Africa |
| Population universe | The people who were present in the country on the night of 9–10 October 2001. People living in households across the country, as well as those in hostels, hotels, hospitals and all other types of communal living quarters, and even the homeless, were all visited. |
| De jure or de facto | De facto |
| Census/survey day | October 10, 2001 |
| Questionnaire | Three different census questionnaires were developed – one for households (the A questionnaire), one for individuals in institutions (the B questionnaire), and one for the institutions themselves (the C questionnaire). The A questionnaire was also used in workers' hostels, student hostels, residential hotels and homes for the independent aged, whilst the B and C questionnaires were also used in tourist hotels and for the homeless. |
| Type of fieldwork | Each enumerator was required to produce one or more completed questionnaires for each dwelling visited. Households were encouraged to be interviewed by the enumerator if possible. Alternatively, a respondent could complete the questionnaire for collection later, where circumstances allowed. Enumerators carried translations of the questions into the other ten official languages, to refer to where necessary. |
| Estimated undercount | Varies by province: 14.07% to 22.51% for individuals; 15.55% to 26.21% for households. |
| Microdata sample characteristics | |
| Sample design | Systematic stratified sample drawn by Statistics South Africa. |
| Sample fraction | 10% |
| Sample size (person records) | 3725655 |
| Sample weights | Computed by census agency and should be used for most types of analysis. |
| Units identified in microdata | |
| Dwellings | No |
| Vacant units | No |
| Households | Yes |
| Collective dwellings | Yes |
| Smallest geography | Magisterial districts and municipalities with 20,000+ population in 2001 |
| Unit definitions | |
| Dwellings | Any structure intended or used for human habitation. |
| Households | A group of persons who live together, and provide themselves jointly with food and/or other essentials for living, or a single person who lives alone. (The 'four-night-a-week' criterion for household membership does not apply, as this was a de facto census, that is, people were counted where they were staying on census night.) |
| Collective dwellings | Living quarters where certain facilities are shared by groups of individuals or households. They include hostels, hotels and institutions. |
| Census/survey characteristics | |
| Type | Survey |
| Title | Community Survey 2007 |
| Statistical agency | Statistics South Africa |
| Population universe | All usual members of the household who stay in the dwelling at least four nights a week and have done so over the last four weeks prior to census date, plus visitors who spent the night before the interview with the household. |
| De jure or de facto | De jure and de facto |
| Census/survey day | 2007-02-07 00:00:00 |
| Field work period | A three week period (February 7-28, 2007) with a non-response follow-up period of one week (March 1-7). |
| Questionnaire | A single "Household Questionnaire" for information on dwelling, household, and individuals. |
| Type of fieldwork | Direct interview |
| Microdata sample characteristics | |
| Sample design | Two-stage, stratified systematic random sampling drawn by the country. Stage I: The sampling frame contains 79,466 enumeration areas (EAs) (the primary sampling units) which are stratified by municipality. Systematic random sampling is used to select EAs within municipalities. In municipalities with fewer than 30 EAs, all EAs are automatically selected. In municipalities with 30+ EAs, a fix proportion of 19% of EAs are selected. If the selected EAs in a municipality are less than 30, the sample in the municipality is increased to 30 EAs. Stage 2: A fixed proportion of 10% of the dwellings in a selected EA are selected. If there are less than 10 dwellings in an EA, the selection is increased to 10 dwelling units. All households within the selected dwelling units are covered. No replacement of refusals, vacant dwellings or non-contacts. Response rate 93.9%. |
| Sample fraction | 0.02 |
| Sample size (person records) | 1047657 |
| Sample weights | Computed by census agency and should be used for most types of analysis. |
| Units identified in microdata | |
| Dwellings | No |
| Vacant units | No |
| Households | Yes |
| Collective dwellings | Yes |
| Smallest geography | Municipalities with 20,000+ population |
| Unit definitions | |
| Dwellings | A structure or part of a structure or group of strucutres occupied or meant to be occupied by one or more households |
| Households | A household is a group of persons who live together and provide themselves jointly with food or other essentials for living, or a single person who lives alone. |
| Collective dwellings | Collective living quarters or communal living quarters are (1) structually separate and independent places of abode intended for habitation by large groups of individuals or several households. Such quarters usually have certain common facilities, such as cooking and ablution facilities, lounges or dormitories which are shared by the occupants. (2) Lving quarters where certain facilities are shared by groups of individulas or households.
Institution: A particular type of collective living quarters, for people with a common characteristic who are living under a common regime. Examples are: hospital/clinic, frail care center, childcare institution/orphanage, etc. |
| Census/survey characteristics | |
| Type | Census |
| Title | Census 2011 |
| Statistical agency | Statistics South Africa |
| Population universe | All persons present in the country on the night of 9-10 October, 2011 |
| De jure or de facto | De facto |
| Census/survey day | 2011-10-10 00:00:00 |
| Field work period | Primarily from 10-31 October, but some enumeration continued until December 2011 |
| Questionnaire | Three separate questionnaires were used to enumerate the household population (form A), transient individuals and individuals staying in hotels on census night (form B), and the institutional population (form C). |
| Type of fieldwork | Direct and self-enumeration |
| Microdata sample characteristics | |
| Sample design | Systematic stratified sample. 1 in 10 sample of household records classified as housing units or converted households, and an independent 1 in 10 sample of persons who resided in other living quarters. Local municipalities were the primary strata and demographic characteristics of persons within the household were used a secondary strata. |
| Sample fraction | 8.5% |
| Sample size (person records) | 4418594 |
| Sample weights | Weights computed by census agency should be used for most types of analysis. |
| Units identified in microdata | |
| Dwellings | No |
| Vacant units | No |
| Households | Yes |
| Collective dwellings | Yes |
| Smallest geography | Municipality |
| Unit definitions | |
| Dwellings | Any structure intended or used for human habitation |
| Households | A household is a group of persons who live together and provide themselves jointly with food or other essentials for living, or a single person who lives alone. |
| Collective dwellings | Living quarters where certain facilities are shared by groups of individuals or households. They can be divided into: (a) hotels, motels, guesthouses, etc.; (b) workers' hostels and students' residences; and (c) institutions. |
| Census/survey characteristics | |
| Type | Survey |
| Title | Community Survey 2016 |
| Statistical agency | Statistics South Africa |
| Population universe | Population residing in private dwellings. |
| De jure or de facto | De facto |
| Census/survey day | March 7, 2016 |
| Field work period | March 7 to April 22, 2016 |
| Questionnaire | A single "Household Questionnaire" for information on dwelling, household, and individuals. All data to be collected on a tablet computer. |
| Type of fieldwork | Direct interview |
| Estimated undercount | A small number of remote enumeration areas and institutional or collective dwellings were omitted from the survey. This results in a slight undercount which as been adjusted in the calculation of the inflation factor. |
| Microdata sample characteristics | |
| Sample design | Systematic stratified sample drawn by Statistics South Africa based on the 2011 census. |
| Sample fraction | 5.8 |
| Sample size (person records) | 3328793 |
| Sample weights | Computed by census agency and should be used for most types of analysis. |
| Units identified in microdata | |
| Dwellings | No |
| Vacant units | No |
| Households | Yes |
| Collective dwellings | No |
| Smallest geography | Municipality |
| Unit definitions | |
| Dwellings | A structure or part of a structure or group of strucutres occupied or meant to be occupied by one or more households |
| Households | A household is a group of persons who live together and provide themselves jointly with food or other essentials for living, or a single person who lives alone. |
| Collective dwellings | Not enumerated |