The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Alternative way for de-normalization when there is no data on the number of households
Alternative way for de-normalization when there is no data on the number of households [message #5483] Fri, 29 May 2015 05:42 Go to next message
albena is currently offline  albena
Messages: 7
Registered: February 2015
Member
Dear DHS-team,

I've been reading about the de-normalization of weights when one combines DHS for several countries or(and) several periods. The problem with finding data on the number of households I guess is nothing new but I wanted to ask you what would be the alternative. It took me really a lot of time to collect data on the number of households for a couple of countries and I did my best to check every census that is available. However I have some cases for which I simply can't find anything. I read somewhere that an alternative would be to use the total population of the country but I'm not sure which would be the adequate DHS measure (e.g., number of couples?) that would be in the denominator of the weighting fraction. Are you aware of any other solution(s)?

I would be very grateful if you could help me with that.

Thanks,
Albena
Re: Alternative way for de-normalization when there is no data on the number of households [message #5486 is a reply to message #5483] Fri, 29 May 2015 09:43 Go to previous message
Trevor-DHS is currently offline  Trevor-DHS
Messages: 787
Registered: January 2013
Senior Member
If you can't find a reasonable estimate of households, you can use the population of women age 15-49 from the UN's World Population Prospects (http://esa.un.org/wpp/unpp/panel_indicators.htm) together with the number of women age 15-49 from the DHS. This should be very similar to the results you would get with using households for the denormalization.
Previous Topic: Weighting Data without SPSS/Stata
Next Topic: Compute sample weight for a dataset
Goto Forum:
  


Current Time: Thu Mar 28 15:47:26 Coordinated Universal Time 2024