The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Ethiopia weighting
Ethiopia weighting [message #11346] Wed, 07 December 2016 06:33 Go to next message
annfitz is currently offline  annfitz
Messages: 5
Registered: April 2015
Member
good afternoon

I want to analyse two Ethiopia data sets, Ethiopia 2005 and 2011, I have several questions re weighting, I would like to combine the data sets, so
1) would the weight variable still be v005/100000 or do I need to recalculate and normalize, if so how would I do this (please give stata command), I would normally just use the weight variable, what additional info would I need and where do I obtain it??
2) re strata, do I need to include a strata variable in the survey set command, if so which variables would I use to calculate the strata, I normally just use the psu variable (v001 or v021, they were identical in the two surveys)
3) re analysis, if I want to compare a subset I would normally use an if statement , or would it be better to use the subset command, I normally use the if method


Dr Ann fitzmaurice
Re: Ethiopia weighting [message #11347 is a reply to message #11346] Wed, 07 December 2016 07:27 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3203
Registered: February 2013
Senior Member
There are several posts on the forum, addressing: weighting, strata and combining datasets. Please search the forum to find related posts.
Previous Topic: Weights for use in sub-population
Next Topic: Rural-Urban sample weights
Goto Forum:
  


Current Time: Sat Dec 7 22:50:13 Coordinated Universal Time 2024