[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Re: Anyone managing to merge DHS datasets using Stata?
The DHS questionnaires will help you identify the data. You can find
the questionnaires in the back of the DHS report for South Africa:
Department of Health (South Africa), Medical Research Council (South
Africa), and ORC Macro. [2002.] South Africa Demographic and Health
Survey 1998. [Pretoria, South Africa: Department of Health.]
I haven't seen the data for South Africa but I have analyzed DHS data
for many other countries. If the South African data comes in the
standard DHS format you can create your own household ID using hv001
(cluster number) and hv002 (household number). In some countries you
also have to include hv024 (region) (this is the case with Indian
data, for example). You can try one of the following:
gen long hhid = hv001*10000 + hv002
gen double hhid = hv024*10000000 + hv001*10000 + hv002
I prefer working with the flat data files, by the way.
--- J Skordis <firstname.lastname@example.org> wrote:
> I am working with the South African Demographic and Health Survey
> in Stata. The dataset is broken into various files which I need
> to merge - the only problem is that merging by hhid and pcode
> won't work as they haven't put an hhid in every file. Instead,
> some files have a caseid which can be constructed in one of two
> ways and I cannot tell which way they created it because I cannot
> merge the files!! Catch 22.
> Anyone working on this (or other) DHS dataset(s) who has found a
> way around this problem, please let me know.
> Jolene Skordis Worrall
> Centre for Social Science Research
> University of Cape Town
> Tel: 650 5785
Do you Yahoo!?
Y! Web Hosting - Let the expert host your web site
* For searches and help try: