The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » India » Re: SAS datasets in NFHS data
Re: SAS datasets in NFHS data [message #1095 is a reply to message #1093] Mon, 06 January 2014 12:06 Go to previous messageGo to previous message
Reduced-For(u)m
Messages: 292
Registered: March 2013
Senior Member
I think the program StatTransfer will change the SAS formats for you, but it costs a couple hundred dollars (if you don't know anyone who has it).

My understanding of (guess at is probably closer) the repeated variables is that it was a choice the DHS made during recoding so that certain variables would always be part of certain sections. Different recodes contain different modules of information, and sometimes those modules require the same information. It is also the case that sometimes the definition changes very slightly from one variable to another as was discussed in relation to rural/urban/town*. Is there a particular variable you were worried about? A first step would just be to see if the variable has exactly the same value for all observations, in which case it wouldn't matter which one you used.

*see http://userforum.measuredhs.com/index.php?t=tree&th=60&a mp;goto=1001&S=03ecac4273cad0ea824286858fa659c9#msg_1001
 
Read Message
Read Message
Read Message
Previous Topic: children sample size NFHS-2 India
Next Topic: Constructing SLI variable in NFHS
Goto Forum:
  


Current Time: Wed Nov 27 10:13:19 Coordinated Universal Time 2024