| Missing data in Kenya 2014 on decision making [message #13911] |
Wed, 24 January 2018 12:15  |
no7321
Messages: 2
Registered: January 2018
Location: usa
|
Member |
|
|
Hi, I'm using Kenya phase 6 (2014) data for a project examining female decision making autonomy. I was surprised to see that among currently married woman (v502=1), the question on "The person who usually decides on respondent's healthcare" has about 10,000 missing responses. My guess is that this question wasn't asked to all currently married people in the country but I haven't been able to find out who else is excluded so that I can avoid having this large number of missing responses in my final analyses.
Any help would be much appreciated, thanks.
Negar
|
|
|
|
| Re: Missing data in Kenya 2014 on decision making [message #14574 is a reply to message #13911] |
Sat, 21 April 2018 21:31  |
kingx025
Messages: 95
Registered: August 2016
Location: Minneapolis. Minnesota
|
Senior Member |
|
|
According to the "universe" information on the IPUMS-DHS website for V734A, the women included in this question for Kenya 2014 were:
Women age 15-49, in households selected for long questionnaire, who are currently married or living with a man.
More broadly: 16,338 women received short form questionnaire for Kenya 2014, so you will get lots of missing/Not in universe cases for many variables in the Kenya 2014 IR files.
You can use the online variable-specific documentation for Kenya 2014 or any of the 117 samples currently included in IPUMS-DHS to check the empirically confirmed universe for variables and avoid confusion and inadvertent errors. Go to idhsdata.org, pick the appropriate unit of analysis (women, children, births, or household members), use the Search function to find variables of interest, click on the variable name, and then check the information on the "universe" tab for samples of interest.
Miriam King
Dr. Miriam King
IPUMS-DHS Project Manager (www.idhsdata.org)
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
