PROVIDE Project Technical Paper 2005:1
February 2005
Creating an IES-LFS 2000
Database in Stata® 1
Abstract
The Income and Expenditure Survey of 2000 is the most recent comprehensive
source of information on income and expenditure patterns of South African
households. This data is used to compile various household-related sub-matrices
for a series of Social Accounting Matrices for South Africa. By linking the Labour
Force Survey of September 2000, which contains detailed employment data on
occupation codes, activity codes and wages of workers, with the Income and
Expenditure Survey of 2000 various factor-related sub-matrices can also be
extracted. This paper discusses the steps followed to extract data, correct
problems and errors where appropriate or necessary, merge various files, and
create Stata format data files that can be used to compile the relevant sub-
matrices. The focus remains highly technical throughout.
1 The main author of this paper is Kalie Pauw, Senior Researcher of the PROVIDE Project. The Stata® software
(referred to throughout as Stata) is a registered trademark of the Stata Corporation (StataCorp, 2001).
i
© PROVIDE Project