The DHS Program User Forum: Weighting data

Home » Data » Weighting data » Colombia DHS 2015

Show: Today's Messages :: Show Polls :: Message Navigator

Colombia DHS 2015 [message #14394]

Mon, 02 April 2018 15:54

antrabhatt
Messages: 4
Registered: April 2018
Location: NY

Member

Hi there,

I am trying to do some analysis by comparing men and women in Colombia for which I have appended the IR file to the MR file. However, the variable v131/mv131 which represents ethnicity seems to have no observations in the MR file. Has anyone else faced this problem? Is there another way to approximate ethnicity for men?

[Updated on: Mon, 02 April 2018 15:54]

Report message to a moderator

Re: Colombia DHS 2015 [message #14399 is a reply to message #14394]

Tue, 03 April 2018 13:20

Bridgette-DHS
Messages: 3224
Registered: February 2013

Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum:

In the IR file, 86% of women (weighted) have "None of the above" for v131. There is not a great deal of ethnic diversity, except in Pacifica (v024=4). As a first approximation, if there are IR cases in the same household as an MR case, you could impute the man's ethnicity to be the same. However, this is definitely not reliable. Perhaps other users will have suggestions.

Report message to a moderator

Re: Colombia DHS 2015 [message #14400 is a reply to message #14399]

Tue, 03 April 2018 13:35

antrabhatt
Messages: 4
Registered: April 2018
Location: NY

Member

Thanks so much! Looks like that is the only plausible solution

Report message to a moderator

Previous Topic:	Variable for weighting
Next Topic:	Components of ANC

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Mon Jan 20 06:24:25 Coordinated Universal Time 2025