Labour Force Survey 2007, September

South Africa, 2007

Get Microdata

Reference ID

zaf-statssa-lfs-2007-sep-v2.1

Producer(s)

Statistics South Africa

Collections

South African Labour Force Survey Data

Metadata

Documentation in PDF DDI/XML JSON

Created on

Jan 10, 2012

Last modified

May 06, 2020

Page views

89022

Downloads

13927

Identification

Survey ID number

zaf-statssa-lfs-2007-sep-v2.1

Title

Labour Force Survey 2007

Subtitle

September

Country

Name	Country code
South Africa	zaf

Study type

Labor Force Survey [hh/lfs]

Series Information

Statistics South Africa. Labour Force Survey: September 2007. [dataset]. Version 2.1. Pretoria: Statistics South Africa [producer], 2008. Cape Town: DataFirst [distributor], 2011. DOI: https://doi.org/10.25828/s06m-8735

Abstract

The LFS is a twice-yearly rotating panel household survey, specifically designed to measure the dynamics of employment and unemployment in South Africa. It measures a variety of issues related to the labour market,including unemployment rates (official and expanded), according to standard definitions of the International Labour Organisation (ILO).

All editions of the LFS have been updated (some more than once) since their release. These version changes are detailed in a document available from DataFirst (in the "external documents" section titled "LFS 2000-2008 Collated Version Notes on the South African LFS").

Kind of Data

Sample survey data [ssd]

Unit of Analysis

Individuals

Version

Version Description

Version 2.1

Version Date

2011

Version Notes

The South African September 2007 LFS dataset was originally released in March 2007 as 2 data files (person and worker), before being immediately retracted due to a number of errors identified by Statistics South Africa. A second version was made available shortly thereafter by Statistics South Africa (version 2.0). A third version was then downloaded by DataFirst in November 2009. This version (version 2.1), the worker data file in particular, differs from version 2.0.

Specifically, the variable "Q31inHHP" (which is a categorical reflecting whether or not the respondent is supported by members of his or her household) differs substantively between versions. In version 2.0, the data shows roughly 13,388 observations responding "No" (a value of 2) and roughly 26,287 assigned the value label "N/A" (data value of 8). This reverses in version 2.1, with 26,287 respondents now listed as "No" and 13,388 listed as "3" for that variable. The value labels of "N/A" and "Unspecified" are no longer in the data file and the actual data values have also changed to 3 and 4. It is assumed that the value 9, previously labelled as "Unspecified", is now simply equivalent to the unlabelled data value "4" (which is no longer labelled at all). This is assumed because the count of observations of that value is the same between versions of the data file, although this may be false given that the observation count reverses for two other values in the same variable. The original metadata specifies that data values of 8 and 9 should be labelled "N/A" and "Unspecified" respectively. The change in the data between versions, then, looks likely to be an error of some kind.

A third version was downloaded by DataFirst in August 2011, which is the same as version 2.1.

Scope

Notes

Demographics, education, economic activity, work for pay, business ownership, unemployment, employers, main work activity in the past week, wages, salary, employment, migration

Topics

Topic	Vocabulary	URI
employment [3.1]	CESSDA
in-job training [3.2]	CESSDA
labour relations/conflict [3.3]	CESSDA
retirement [3.4]	CESSDA
unemployment [3.5]	CESSDA
working conditions [3.6]	CESSDA
LABOUR AND EMPLOYMENT [3]	CESSDA
TRADE, INDUSTRY AND MARKETS [2]	CESSDA
DEMOGRAPHY AND POPULATION [14]	CESSDA

Coverage

Geographic Coverage

National coverage

Geographic Unit

Province (variable name: "Prov")
District Council/Metro (variable name: "DC")

Universe

The LFS sample covers the non-institutional population except for workers' hostels. However, 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.

Producers and sponsors

Primary investigators

Name
Statistics South Africa

Sampling

Sampling Procedure

Statistics South Africa uses a rotating panel methodology for the labour force survey. The rotating panel methodology involves visiting the same dwelling units on a number of occasions (in this instance, five at most). After the panel is established, a proportion of the dwelling units is replaced each round (in this instance, 20%). New dwelling units are added to the sample to replace those that are taken out.

Enumeration Areas (EAs) that had a household count of less than twenty-five were omitted from the census 2001 frame that was used to draw the sample of Primary Sampling Units (PSUs) for the new Master Sample. Other omissions from the Master Sample frame included all institution EAs except workers, hostels, convents and monasteries. EAs from census 2001 were pooled in two stages, before and after sampling. Before sampling the criterion that was used to pool EAs was that they should contain a minimum of one hundred households. However, during listing it was discovered that there were discrepancies between the information on the database and what was on the ground.

Therefore, in the second stage of pooling, EAs that were found to have less than sixty dwelling units during listing were pooled. The Master Sample is a multi-stage stratified sample. The overall sample size of PSUs was 3000. The explicit strata were the 53 district councils/metros (DCs). The 3000 PSUs were allocated to these DCs using the power allocation method. The PSUs were then sampled using probability proportional to size principles. The measure of size used was the number of households in a PSU as calculated in the census. The sampled PSUs were listed with the dwelling unit as the listing unit. From these listings systematic samples of dwelling units per PSU were drawn. These samples of dwelling units form clusters. The size of the clusters differs depending on the specific survey requirements. The LFS uses one of the clusters that contain ten dwelling units.

Weighting

The initial weights (household weights), based on the sample design, were equal to the inverse of the probability of selection. The initial weight for each member of the household was the same as the weight for the household itself. Further adjustment factors were then calculated within PSUs to account for non-response. To adjust for under-enumeration and to align survey estimates with independent population estimates, the weights were calibrated against Person benchmarks. A software package called CALMAR was used to perform this calibration. Using an iterative procedure, CALMAR adjusted the weights so that Person estimates conformed as closely as possible to external Person benchmarks. Gender, race and age group parameters were used for the Person cross-classification of the population.

Data collection

Dates of Data Collection

Start	End
2007-09	2007-09

access_policy

Access authority

Name	Affiliation	URL	Email
DataFirst	University of Cape Town		info@data1st.org

Access conditions

Licensed dataset, accessible under conditions

Citation requirements

Disclaimer and copyrights

Contacts

Name	Affiliation	Email	URL
DataFirst Helpdesk	University of Cape Town	support@data1st.org

Metadata production

DDI Document ID

ddi-zaf-datafirst-lfs-2007-sep-v1.1

Producers

Name	Affiliation	Role
DataFirst	University of Cape Town	DDI Producer

Date of Metadata Production

2020-03-30

Metadata version

DDI Document version

Version 2

Back to Catalog