The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Sampling » Strata specification across multiple surveys
Re: Strata specification across multiple surveys [message #9277 is a reply to message #9233] Wed, 02 March 2016 11:49 Go to previous messageGo to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2552
Registered: February 2013
Senior Member
Following is a response from Senior DHS Stata Specialist, Tom Pullum:


A list of the strata in all surveys is being prepared. I'm sorry that it is not yet available. I will remind the person who is preparing it.

A cross of v024 and v025 will always be very close to correct. In some files, v022 is provided but is incorrect. If you just do "tab v022" or "codebook v022" and find that there are many (e.g. more than 70) values and only a small number of households (e.g. the households in two clusters) in each stratum, it means that v022 is not correct, and it will be safer to include v024 x v025. In some of the older surveys, a pairing of clusters was part of the design and somehow those pairs were incorrectly put into v022.

Your surveys are so recent that I think v022 will be correct or, at worst, missing. I don't think the previous paragraph will apply.

 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: definition of urban areas
Next Topic: Design Effects across surveys
Goto Forum:
  


Current Time: Thu Aug 18 22:54:14 Coordinated Universal Time 2022