Abstract

Every person, household and institution present in South Africa on Census Night, 9-10 October 1996, should have been enumerated in Census 1996. The purpose of the census was to provide a count of all persons present within the territory of the Republic of South Africa at that time. More specifically, the purpose of this census was to collect, process and disseminate detailed statistics on population size, composition and distribution at a small area level.

Geographic coverage

The South African Census 1996 has national coverage.

Analysis unit

Households and individuals

Universe

The South African census 1996 covered every person present in South Africa on Census Night, 9-10 October 1996 (except foreign diplomats and their families).

Kind of data

Census enumeration data

Sampling procedure

The data in the South African Census 1996 data file is a 10% unit level sample drawn from Census 1996 as follows:

1) Households: • A 10% sample of all households (excluding special institutions and hostels)

2) Persons: • A 10% sample of all persons as enumerated in the 1996 Population Census in South Africa

The census household records were explicitly stratified according to province and district council. Within each district council the records were further implicitly stratified by local authority. Within each implicit stratum the household records were ordered according to the unique seven-digit census enumerator area number, of which the first three digits are the (old) magisterial district number.

Mode of data collection

Face-to-face [f2f]

Research instrument

Different methods of enumeration were used to accommodate different situations and a variety of questionnaires were used. The information collected with each questionnaire differed slightly. The questionnaires used were as follows:

Questionnaire 1: (Household and personal questionnaire) This questionnaire was used in private households and within hostels which provided family accommodation. It contained 50 questions for each person and 15 for each household. Every household living in a private dwelling should have been enumerated on a household questionnaire. This questionnaire obtained information about the household and about each person who was present in the household on census night.

Questionnaire 2: (Summary book for hostels) This questionnaire was used to list all persons/households in the hostel and included 9 questions about the hostel. A summary book for hostels should have been completed for each hostel (that is, a compound for workers provided by mines, other employers, municipalities or local authorities). This questionnaire obtained information about the hostel and also listed all household and/or persons enumerated in the hostel. Some hostels contain people living in family groups. Where people were living as a household in a hostel, they were enumerated as such on a household questionnaire (which obtained information about the household and about each person who was present in the household on Census Night). On the final census file, they will be listed as for any other household and not as part of a hostel. Generally, hostels accommodate mostly individual workers. In these situations, persons were enumerated on separate personal questionnaires. These questionnaires obtained the same information on each person as would have been obtained on the household questionnaire. The persons will appear on the census file as part of a hostel. Some hostels were enumerated as special institutions and not on the questionnaires designed specifically for hostels.

Questionnaire 3: (Enumerator's book for special enumeration) This questionnaire was used to obtain very basic information for individuals within institutions such as hotels, prisons, hospitals etc. as well as for homeless persons. Only 6 questions were asked of these people. The questionnaire also included 9 questions about the institution. An enumerator's book for special enumeration should have been completed for each institution such as prisons and hospitals. This questionnaire obtained information on the institution and listed all persons present. Each person was asked a brief sub-set of questions - just 7 compared to around 50 on the household and personal questionnaires. People in institutions could not be enumerated as households. Homeless persons were enumerated during a sweep on census night using a special questionnaire. The results were later transcribed to standard enumerator's books for special enumeration to facilitate coding and data entry.

Response rate

The final calculation of the undercount of persons, based on analysis of a post-enumeration survey (PES) conducted shortly after the original census, was performed by Statistics South Africa. The estimated reponse rates are detailed below, both according to stratum and for the country as a whole. An estimated 10,7% of the people in South Africa, through the course of the census process, were not enumerated. For more information on the undercount and PES, see the publication, "Calculating the Undercount in Census '96", Statistics South Africa Report No. 03-01-18 (1996) which is included in the external documents section.

Undercount of persons by province (stratum, in %):

Western Cape 8,69
Eastern Cape 10,57
Northern Cape 15,59
Free State 8,75
KwaZulu-Natal 12,81
North West 9,37
Gauteng 9,99
Mpumalanga 10,09
Northern Province 11,28

South Africa 10,69

Abstract

The Quarterly Labour Force Survey (QLFS) is a household-based sample survey conducted by Statistics South Africa (Stats SA). It collects data on the labour market activities of individuals aged 15 years or older who live in South Africa.

Geographic coverage

National coverage

Analysis unit

Individuals

Universe

The QLFS sample covers the non-institutional population of South Africa with one exception. The only institutional subpopulation included in the QLFS sample are individuals in worker's hostels. Persons living in private dwelling units within institutions are also enumerated. For example, within a school compound, one would enumerate the schoolmaster's house and teachers' accommodation because these are private dwellings. Students living in a dormitory on the school compound would, however, be excluded.

Kind of data

Sample survey data [ssd]

Sampling procedure

The Quarterly Labour Force Survey (QLFS) uses a master sample frame which has been developed as a general-purpose household survey frame that can be used by all other Stats SA household surveys that have reasonably compatible design requirement as the QLFS. The 2013 master sample is based on information collected during the 2011 population Census conducted by Stats SA. In preparation for Census 2011, the country was divided into 103 576 enumeration areas (EAs). The census EAs, together with the auxiliary information for the EAs were used as the frame units or building blocks for the formation of primary sampling units (PSUs) for the master sample since they covered the entire country and had other information that is crucial for stratification and creation of PSUs. There are 3 324 primary sampling units (PSUs) in the master sample with an expected sample of approximately 33 000 dwelling units (DUs). The number of PSUs in the current master sample (3 324) reflects an 8,0% increase in the size of the master sample compared to the previous (2007) master sample (which had 3 080 PSUs). The larger master sample of PSUs was selected to improve the precision (smaller CVs) of the QLFS estimates.

The master sample is designed to be representative at provincial level and within provinces at metro/non-metro levels. Within the metros, the sample is further distributed by geographical type. The three geography types are:urban, tribal and farms. This implies, for example, that within a metropolitan area, the sample is representative of the different geography types that may exist within that metro. It is divided equally into four sub-groups or panels called rotation groups. The rotation groups are designed in such a way that each of these groups has the same distribution pattern as that which is observed in the whole sample. They are numbered from one (1) to four (4) and these numbers also correspond to the quarters of the year in which the sample will be rotated for the particular group.

There are a number of aspects in which the 2013 version of the master sample differs from the 2007 version. In particular, the number of primary sample units increased. Mining strata were also introduced which serves to improve the efficiency of estimates relating to employment in mining. The number of geo-types was reduced from 4 to 3 while the new master sample allows for the publication of estimates of the labour market at metro level. The master sample was also adjusted Given the change in the provincial distribution of the South African population between 2001 and 2011. There was also an 8% increase in the sample size of the master sample of PSUs to improve the precision of the QLFS estimates. The sample size increased most notable in Gauteng, the Eastern Cape and KwaZulu-Natal. For more details on the differences between the two master samples please consult the section 8 (technical notes) of the QLFS 2015 Q3 release document (P0211).

From the master sample frame, the QLFS takes draws exmploying a stratified two-stage design with probability proportional to size (PPS) sampling of PSUs in the first stage, and sampling of dwelling units (DUs) with systematic sampling in the second stage. The primary stratification occurred at provincial, metro/non-metro, mining and geography type while the secondary strata were created within the primary strata based on the demographic and socio-economic characteristics of the population.

For each quarter of the QLFS, a ¼ of the sampled dwellings is rotated out of the sample. These dwellings are replaced by new dwellings from the same PSU or the next PSU on the list. Thus, sampled dwellings are expected to remain in the sample for four consecutive quarters. It should be noted that the sampling unit is the dwelling, and the unit of observation is the household. Therefore, if a household moves out of a dwelling after being in the sample for, two quarters and a new household moves in, the new household will be enumerated for the next two quarters. If no household moves into the sampled dwelling, the dwelling will be classified as vacant (or unoccupied).

Mode of data collection

Face-to-face [f2f]

Data appraisal

Industry Coding in the QLFS

The QLFS variable Q43INDUSTRY shows the industry in which household members are employed. The data is collected from Questions 4.3.a and 4.3.b, which were write-in questions. The responses to these two questions were used to determine the type of industry. Industry was coded to three digits on the basis of Industrial Classification of all Economic Activities (SIC) standard industry codes. However, the SIC codes used in the QLFS are not the latest (version 7 2012) but an older standard industry code list, v5. This code list is available at http://www.statssa.gov.za/classifications/codelists/sic.zip.

Geographic coverage

National Coverage

Universe

The target population is all births recorded on the NPR between 1998 and 2010 for South African citizens and permanent residents, regardless of which year the birth occurred. All births that occurred in South Africa with parents being non-South African citizens or not permanent residents were excluded.

Sampling procedure

The registration of births in South Africa is governed by the Births and Deaths Registration Act, 1992 (Act No. 51 of 1992), as amended, and is administered by the Department of Home Affairs (DHA) using Form DHA-24 (Notice of birth), which recently replaced Form BI-24 that was previously used. Notice of the birth must be given by one of the parents or; if neither parent is available to do so, the person having charge of the child or a person requested by the parents to do so. The person requested to register the birth must have a written mandate from the child's parents which must also include the reasons why neither of the parents is in a position to register the birth. The birth of a child outside the country; where at least one parent is a South African citizen; can be registered at any South African Mission abroad.Documentary proof in the form of a birth certificate of the foreign country must accompany the Notice of Birth.

The Act states that a child must be registered within 30 days of birth. Where the notice of a birth is given after the expiration of 30 days from the date of the birth, the Director-General may demand that reasons for the late notice be furnished and that the fingerprints be taken of the person whose notice of birth is given. Where the notice of a birth is given for a person aged 15 years and older, the birth shall be registered if it complies with the prescribed requirements for a late registration of birth.

Following the registration of a birth, a birth certificate is issued by the DHA. Citizens and permanent residents receive computer-printed abridged birth certificates and non-citizens receive handwritten certificates. The information of South African citizens and permanent residents is captured on the National Population Register (NPR).

The following persons and particulars are eligible to be included on the NPR:

• All children born of South African citizens and permanent residents when the notice of the birth is given within one year after the birth of the child.

• All children born of South African citizens and permanent residents when the notice of the birth is given one year after the birth of the child; together with the prescribed requirement for a late registration of birth.

• All South African citizens and permanent residents who, upon attainment of the age of 16, applied for and were granted identification cards (or books).

• All South African citizens and permanent residents who die at any age after birth.

• All South African citizens and permanent residents who depart permanently from South Africa.

The DHA captures information on places based on magisterial districts using the twelfth edition of the Standard Code List of Areas (Central Statistics Services, 1995). Stats SA then recodes the magisterial districts into district councils (DCs), metropolitan areas (metros) and provinces based on the 2011 municipal boundaries. The data sets for 1998 to 2010 have all been recoded according to the 2011 municipal boundaries.

It should be noted that the distribution of births by DCs, metros and provinces are approximate figures; as there was no perfect match of magisterial districts for all DCs, metros and provinces since some magisterial districts are situated in more than one DC, metro or province. Such magisterial districts were allocated to the district council where the majority of the land area falls (see the folder on maps). The only exception was with Nigel in Gauteng province. The majority of the land area of Nigel magisterial district is in Sedibeng district council (which is mainly farm areas and therefore sparsely populated) while the majority of the population lives in Ekurhuleni metropolitan area. As such, Nigel was classified to Ekurhuleni and not Sedibeng.

Magisterial district of birth refers to the district of birth occurrence for births registered before 15 years of age. For those that were registered from 15 years of age, district refers to the district of birth registration. Furthermore, from 2009, the processing of late birth registrations from age 15 were centralised at the DHA head office in Pretoria. As such, the late birth registrations processed in Pretoria from 15 years have a district code of Pretoria; even if they occurred in other areas. There were a few exceptional cases which were registered in Pretoria; but were not captured using the Pretoria code.

Mode of data collection

Other [oth]

Research instrument

NOTICE OF BIRTH - [Births and Deaths Registration Act 51 of 1992]

A. DETAILS OF THE CHILD

B. DETAILS OF FATHER (PARENT A)

C. DETAILS OF MOTHER (PARENT B)

D. ACKNOWLEDGEMENT OF PATERNITY OF A CHILD BORN OUT OF WEDLOCK

E. DETAILS OF THE LEGAL GUARDIAN/SOCIAL WORKER*

F. DECLARATION

G. FOR OFFICIAL USE ONLY - OFFICE OF ORIGIN

Cleaning operations

Data capturing of information on births is done by DHA officials. The data is captured directly onto the Population Register Database at Nucleus Bureau. These transactions are used to update the database of the NPR and the population register database. As soon as the DHA has captured the data; the data is made available on the mainframe. The data is then downloaded via ftp; or collected from the State Information Technology Agency (SITA) written on a CD by Stats SA. For the purpose of producing vital statistics, the following system is followed: all the civil transactions carried out at all DHA offices are written onto a cassette every day. At the end of every month, a combined set of cassettes is created containing all the transactions done for the month. These transactions are downloaded and the birth transactions are extracted for processing at Stats SA. The year in which the births are registered is the registration year. Using this information, Stats SA provides a breakdown of the registered births according to the year in which the births occurred.

While birth information sent to Stats SA is the same as that in the population register, there is a difference in the format between the two. On one hand, Stats SA’s data are based on births registered during the year (registration-based), while on the other hand, entries in the population register reflect the date of birth.

Data appraisal

Users are cautioned on the following limitations of the data:

• Father’s age had a high percentage of cases where information was unspecified or unknown for all the years.
• Data for 1998 and 1999 have incorrect information on month of birth, which could not be resolved.

Note: - Unknown : refers to cases where the answer provided is not correct or not possible given the options available. - Unspecified: refers to cases where no response was given.

Abstract

The Time Use Survey (TUS) is a household-based survey that measures and analyses the time spent by women and men, girls and boys, the rich and the poor, on different activities over a specified period. Statistics South Africa (Stats SA) conducts time use surveys using the 'yesterday' diary approach. A 'yesterday' diary is one in which the respondent is asked what they did for each period in the 24 hours of a day preceding the survey interview. Unlike data from other surveys, time use data reflects what activities are performed, how they are performed and how long it takes to perform such activities. Such activities include paid work, unpaid work, volunteer work, domestic work, leisure and personal activities.

Stats SA conducted the first TUS in 2000 and the second one in 2010. The TUS aims to provide information on the division of both paid and unpaid labour between women and men, shed light on the reproductive and leisure activities of household members, and provide information about less well-understood productive activities such as subsistence work, casual work and work in the informal sector. Therefore, TUS surveys can be used for gender policy analysis in relation to employment and unemployment, services for children, the elderly and people with disabilities, and provision of basic household services such as electricity and water that obviate the need for manual collection of fuel and water for household use.

Geographic coverage

The survey has national coverage

Analysis unit

Households and individuals

Universe

The TUS sample covered the non-institutional population aged 10 years and above excluding those living in worker hostels - thus representing an estimated 39,9 million people.

Kind of data

Sample survey data

Sampling procedure

The TUS 2000 sample frame was based on the frame prepared for the 1999 Survey of activities of young people (SAYP). This sample frame was based on the 1996 population census enumerator areas (EAs) and the number of households counted in the 1996 population census. The sampled population excluded all prisoners in prison, patients in hospital, people residing in boarding houses and hotels (whether temporary or semi-permanent), and boarding schools. The 16 EA types from the 1996 Population Census were condensed into four area types, or strata. The four strata were formal urban, informal urban, non-commercial farming rural, and commercial farming areas. Institution type EAs were excluded from the sample.

The sample is based on a stratified two-stage design with probability proportional to size (PPS) sampling of primary sampling units (PSUs) in the first stage, and sampling of dwelling units (DUs) with systematic sampling in the second stage. The EAs were explicitly stratified by province, and within a province by the four strata. The sample size (10 800 dwelling units, with 3 600 units in each of the three tranches) was disproportionately allocated to the explicit strata using the square root method. Within the strata, the EAs were ordered by magisterial district and the EA-types included in the area type (implicit stratification). PSUs consisted of an EA of at least 100 dwelling units. Where an EA contained less than 100 dwelling units, EAs were pooled (using Kish's method of pooling) to meet this requirement. Most EAs had fewer than 100 dwelling units. The dwelling unit was taken as the ultimate sampling unit (USU).

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the TUS is comprised of five sections:

Section 1 - details of all household members Section 2 - demographic details of the first person selected (respondent one) in each household Section 3 - recorded activities performed by respondent one in each household (diary) Section 4 - demographic details of the second person selected (respondent two) in each household Section 5 - recorded activities performed by respondent two in each household (diary)

The diary was divided into half-hour slots. Respondents were asked an open-ended question on the activities performed during each half-hour period. These activities were then post-coded by the fieldworker according to the activity classification system. The respondent could report up to three activities for each time slot. Where there was more than one activity reported for a half hour, the respondent was asked whether these activities were conducted simultaneously, or one after the other.

The sections of the questionnaire for household and demographic data collection also contained additional questions on issues likely to affect time use. For example questions on access to household appliances owned. The questionnaire includes two location codes for each recorded activity. The first code provides for eight broadly-defined locations plus the mobile activity of travel. Where the location of a particular activity could be classified as more than one of the given options, the option highest on the list took precedence. The second code distinguished whether the activity was done inside or outside for the eight broadly-defined locations, and distinguished the mode of travel for all travel activity.

Abstract

The Time Use Survey (TUS) is a household-based survey that measures and analyses the time spent by women and men, girls and boys, the rich and the poor, on different activities over a specified period. Statistics South Africa (Stats SA) conducts time use surveys using the 'yesterday' diary approach. A 'yesterday' diary is one in which the respondent is asked what they did for each period in the 24 hours of a day preceding the survey interview. Unlike data from other surveys, time use data reflects what activities are performed, how they are performed and how long it takes to perform such activities. Such activities include paid work, unpaid work, volunteer work, domestic work, leisure and personal activities.

Stats SA conducted the first TUS in 2000 and the second one in 2010. The TUS aims to provide information on the division of both paid and unpaid labour between women and men, shed light on the reproductive and leisure activities of household members, and provide information about less well-understood productive activities such as subsistence work, casual work and work in the informal sector. Therefore, TUS surveys can be used for gender policy analysis in relation to employment and unemployment, services for children, the elderly and people with disabilities, and provision of basic household services such as electricity and water that obviate the need for manual collection of fuel and water for household use.

Geographic coverage

The survey has national coverage

Analysis unit

Households and individuals

Universe

The TUS sample covered the non-institutional population aged 10 years and above excluding those living in worker hostels - thus representing an estimated 39,9 million people.

Kind of data

Sample survey data

Sampling procedure

The Time Use Survey (TUS) utilised the frame developed as a general-purpose household survey frame that can be used by all other household surveys irrespective of the sample size of the survey. The sample size for the TUS is roughly 30 000 dwellings.The sample is based on information collected during the 2001 Population Census conducted by Stats SA. In preparation for the 2001 Census, the country was divided into 80 787 enumeration areas (EAs). Stats SA's household-based surveys use a master sample of primary sampling units (PSUs) which comprises EAs that are drawn from across the country. The sample is designed to be representative at provincial level and within provinces at metro/non-metro level. Within the metros, the sample is further distributed by geography type. The four geography types are: urban formal, urban informal, rural formal and tribal areas.

The current sample size is 3 080 PSUs divided equally into four subgroups or panels called rotation groups. The rotation groups are designed in such a way that each of these groups has the same distribution pattern as that which is observed in the whole sample. They are numbered from one to four and these numbers also correspond to the quarters of the year in which the sample will be rotated for the particular group. The sample for TUS is based on a stratified two-stage design with probability proportional to size (PPS) sampling of PSUs in the first stage, and sampling of dwelling units (DUs) with systematic sampling in the second stage.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the TUS is comprised of five sections:

Section 1 - details of all household members Section 2 - demographic details of the two selected individuals in a household Section 3 - economic activities of the two selected individuals in a household Section 4 - main work activity of the two selected individuals in a household Section 5 - recorded activities performed by the selected person in a household (diary)

The diary was divided into half-hour slots. Respondents were asked an open-ended question as to the activities performed during a given half-hour. These activities were then post-coded by the fieldworker according to the activity classification system.The respondent could report up to three activities for each time slot. Where there was more than one activity reported for a half hour, the respondent was asked whether these activities were done simultaneously, or one after the other.

The questionnaire includes two location codes for each recorded activity. The first code provides for eight broadly-defined locations plus the mobile activity of travel. Where the location of a particular activity could be classified as more than one of the given options, the option highest on the list took precedence. The second code distinguished whether the activity was done inside or outside for the eight broadly-defined locations, and distinguished the mode of travel for all travel activity.

Data appraisal

Question 1.4 in the questionnaire for the Time Use Survey 2010 is about the travel distance for wood/dung collection. It has six response options. Option 6 (Not Applicable) would be for the households not relying on wood/dung for fuel. However, the corresponding variable in the data file "Q14FarWood" has seven choices, including 'Other', which has quite significant number of responses (720 households). And these 'Other' households still have responses for Q1.5 about 'who's collecting wood/dung'. So they cannot relate to missing responses. It is not clear what this "Other" response category is and Statistics SA has been approached for further information.

Abstract

The Beijing Platform for Action which emerged from the 1995 Fourth United Nations World Conference on Women called for the development of 'suitable statistical means to recognise and make visible the full extent of the work of women and all their contributions to the national economy, including their contribution in the unremunerated and domestic sectors'. During 2000, Statistics South Africa (Stats SA) conducted the fieldwork for the first national time use study in the country. The aim of the survey was to provide information on the way in which different individuals in South Africa spend their time. Such information contributes to greater understanding of policymakers on the economic and social well-being of different societal groups. In particular, the study was intended to provide new information on the division of both paid and unpaid labour between women and men, and greater insight into less well understood productive activities such as subsistence work,casual work and work in the informal sector.

The survey thus had dual objectives: (1) improvement of concepts, methodology and measurement of all types of work and work-related activity, and (2) the feeding of information into better policy-making, with a particular focus on gender equity.

Geographic coverage

The survey had national coverage

Analysis unit

Units of analysis for the survey include households and individuals

Universe

The survey covered household members in South Africa, ten years old and above

Kind of data

Sample survey data [ssd]

Sampling procedure

The time use study sample frame was based on the frame prepared for the 1999 Survey of activities of young people (SAYP). This sample frame was based on the 1996 population census enumerator areas (EAs) and the number of households counted in the 1996 population census. The sampled population excluded all prisoners in prison, patients in hospital, people residing in boarding houses and hotels (whether temporary or semi-permanent), and boarding schools. The 16 EA types from the 1996 Population Census were condensed into four area types, or strata. The four strata were formal urban, informal urban, non-commercial farming rural, and commercial farming areas. Institution type EAs were excluded from the sample.

The EAs were explicitly stratified by province, and within a province by the four strata. The sample size (10 800 dwelling units, with 3 600 units in each of the three tranches) was disproportionately allocated to the explicit strata using the square root method. Within the strata, the EAs were ordered by magisterial district and the EA-types included in the area type (implicit stratification). Primary sampling units (PSUs) consisted of an EA of at least 100 dwelling units. Where an EA contained less than 100 dwelling units, EAs were pooled (using Kish's method of pooling) to meet this requirement. Most EAs had fewer than 100 dwelling units. The dwelling unit was taken as the ultimate sampling unit (USU).

Firstly, a two stage sampling procedure was applied. The allocated number of PSUs was systematically selected with probability proportional to size in each explicit stratum (with the measure of size being the number of dwelling units in a PSU). In each PSU, a systematic sample of 12 households was drawn.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the time use survey was comprised of three sections. Section one covered details of the household. Section two covered demographic details of the first person selected as a respondent in that household. Section three consisted of a Background and methodology diary in which to record the activities performed by the first person selected during the 24 hours between 4 am on the day preceding the interview and 4 am on the day of the interview. Sections four and five were for the second selected person in the household but were otherwise identical to sections two and three respectively.

The household and demographic sections of the questionnaire contained many of the standard questions of Stats SA household surveys. This was done so as to facilitate comparison across surveys. These sections also contained some additional questions on issues that would be likely to affect time use. For the household section, for example, there were questions on access to household aids such as washing machines and vacuum cleaners. In the demographic section there were questions about the presence of the respondent's young children in the household.

The diary, which forms the core instrument of a time use study, was divided into half-hour slots. Respondents were asked an open-ended question as to the activities performed during a given half-hour. These activities were then post-coded by the fieldworker according to the activity classification system (see below). The respondent could report up to three activities for each time slot. Where there was more than one activity reported for a half hour, the respondent was asked whether these activities were conducted simultaneously, or one after the other. For each recorded activity, the questionnaire also included two location codes. The first code provides for eight broadly defined locations plus the mobile activity of travel. Where the location of a particular activity could be classified as more than one of the given options, the option highest on the list took precedence. For example, a domestic worker was classified as working in someone else's dwelling rather than in a workplace. The second code distinguished between interior (inside) and exterior (outside) for the eight broadly-defined locations, and distinguished the mode of travel for all travel activity.

Cleaning operations

The data from the diary were captured in Sybase at Stats SA head office through a custom-designed data capture programme. The programme contained some in-built checks. Further checks were done manually prior to and after capture. The data were subsequently downloaded into SAS format, and the SAS programme was used for analysis.

Abstract

Censuses are principal means of collecting basic population and housing statistics required for social and economic development, policy interventions, their implementation and evaluation. The Post-Apartheid South African government has conducted three Censuses, in 1996, 2001 and 2011.

Geographic coverage

The South African Census 2011 has national coverage.

Analysis unit

Households and individuals

Universe

The South African Census 2011 covered every person present in South Africa on Census Night, 9-31 October 2011 including all de jure household members and residents of institutions.

Kind of data

Census/enumeration data

Sampling procedure

The sampling frame for the PES was the complete list of Census 2011 EAs, amounting to 103 576 EAs. The primary sampling units (PSUs) were the Census EAs. The principle for selecting the PES sample is that the EA boundaries for sampled EAs should have well defined boundaries, and these boundaries should correspond with those of Census EAs to allow for item-by-item comparison between the Census and PES records. The stratification and sampling process followed will allow for the provision of estimates at national, provincial, urban (geography type = urban) and non-urban (geography type = farm and traditional) levels, but estimates will only be reliable at national and provincial levels. The sample of 600 EAs was selected and allocated to the provinces based on expected standard errors which were based on those obtained in PES 2001. Populations in institutions (other than Workers' Hostels), floating and homeless individuals were excluded from the PES sample.

The data files in the dataset include Household, Person, and Mortality files. The 10% sample for the Mortality data file was sampled separately and is not the same as the 10% sample for Household file and Person file.

Mode of data collection

Face-to-face

Research instrument

Three sets of questionnaires were developed for Census 2011: 1. Questionnaire A - the household questionnaire - administed to the population in a household set-up including those households that were found within an institution, such as staff residences 2. Questionnaire B - the population in transit (departing) and those on holiday on reference night (9/10 October 2011). The homeless were also enumerated using this set of questions 3. Questionnaire C - the institutions questionnaire administered to the population in collective living quarters (people who spent census night 9/10 October 2011 at the institution)

A Post-Enumeration Survey was carried out after the census, which used a PES questionnaire.

Sampling error estimates

Comparison of Census 2011 with previous Censuses requires alignment of the data to 2011 municipal boundaries Questions on disability asked in former censuses were replaced in census 2011 with General health and functioning questions. Misreporting on general health and functioning for children younger than five years means data for this variable are only profiled for persons five years and older.

Data appraisal

The dataset does not have a code list for the “geotype” variable which has 3 values (1,2,3).

Abstract

The October Household Survey is an annual survey based on a survey of a large number of households (ranging from 16 000 in 1996 through to 30 000 in 1997 and 1998, depending on the availability of funding). It covers a range of development indicators, including unemployment rates (official and expanded), according to standard definitions of the International Labour Organisation (ILO).

Geographic coverage

The survey had national coverage.

Analysis unit

Households and individuals

Universe

The survey covered households and household members in households in the nine provinces of South Africa

Kind of data

Sample survey data

Sampling procedure

A sample of 20 000 households was drawn in 2 000 enumerator areas (EAs) (that is 10 households per enumerator area). A two-stage sampling procedure was applied and the sample was stratified, clustered and selected to meet the requirements of probability sampling. The sample was based on the 1996 Population Census enumerator areas and the estimated number of people from the administrative records of the 1996 population Census. The sampled population excluded all prisoners in prisons, patients in hospitals, people residing in boarding houses and hotels (whether temporary or semi-permanent). The sample was explicitly stratified by province, Transitional Metropolitan Council (TMC)and District Council (DC). A square root method was used for the allocation of the sample EAs to the explicit strata.

Within each explicit stratum the EAs were stratified by simply arranging them in geographical order by magisterial district and, within the magisterial district, by EA. The allocated number of EAs was systematically selected with probability proportional to size in each stratum. The measure of size was the estimated number of people in Each EA. A systematic sample of 10 households was drawn.

Mode of data collection

Face-to-face [f2f]

Research instrument

The data files in the October Household Survey 1997 (OHS 1997) correspond to the following sections in the questionnaire:
PERSON: Indivitual-level data from Section 1 and Section 4; BIRTHS: Data from Section 2; CHILDREN: Data from Section2; WORKER: Data from Section 3; MIGRANT: Data from Section 5; DEATHS: Data from Section 6; MIGRATION: Data from Section 7; DOMESTIC: Data from Section 8; HOUSE: Household-level data from Section 9

Errors in the marital codes in the original OHS 1998 questionnaire: The questionnaire for the OHS 1998 originally provided by Statistics SA with the data files was incorrect. It was the OHS 1997 questionnaire with a OHS 1998 flap. The marital codes were different in the two surveys. In 1997, the codes for the variable Marital Status were: 1 Never married 2 Married - civil 3 Married - customary 4 Living together 5 Widowed 6 Divorced

In the 1998 survey, the codes for the variable Marital Status are:

1 Married - civil 2 Married - traditional (customary) 3 Living together 4 Widower/widow 5 Divorced/separated 6 Never married

DataFirst notified Statistics SA of this error on 13 July 2007 and they sent a corrected questionnaire. The correct questionnaire is version 2, available with the data since 2007.

Data appraisal

Errors in the marital codes in the original OHS 1998 questionnaire:

The questionnaire for the OHS 1998 originally provided by Statistics SA with the data files was incorrect. It was the OHS 1997 questionnaire with a OHS 1998 flap. The marital codes were different in the two surveys. In 1997, the codes for the variable Marital Status were: 1 Never married 2 Married - civil 3 Married - customary 4 Living together 5 Widowed 6 Divorced

In the 1998 survey, the codes for the variable Marital Status are:

1 Married - civil 2 Married - traditional (customary) 3 Living together 4 Widower/widow 5 Divorced/separated 6 Never married

DataFirst notified Statistics SA of this error on 13 July 2007 and they sent a corrected questionnaire. The correct questionnaire is version 2, available with the data since 2007.