| either to take women's file, kids file, PR file or to merge household file with another in NFHS-4 [message #14765] |
Fri, 04 May 2018 02:43  |
SHIRISHA
Messages: 3
Registered: May 2018
Location: India
|
Member |
|
|
|
We are looking at birth order and its effect on nutrition status differing by gender of the child. So, we are confused as to which file we should take from NFHS-4 data.Either PR file alone will do or kids file needs to be merged with Household file. As we have take z-scores of each child in the household so that we can control stunting for birth order. Please, help us out if anyone knows it as soon as possible. Thanks in advance.
|
|
|
|
|
|
|
|
|
|
| Re: either to take women's file, kids file, PR file or to merge household file with another in NFHS-4 [message #14851 is a reply to message #14846] |
Wed, 09 May 2018 09:34  |
boyle014
Messages: 78
Registered: December 2015
Location: Minneapolis
|
Senior Member |
|
|
Dear Shirisha,
If you use IPUMS-DHS, you do not need to merge the files. Nearly all of the women and household variables are available when children are selected as the unit of analysis.
You can use the Topics drop down menu to browse for the variables that interest you. Child sex is "kidsex", birth order is "kidbord". These are both under the Child Core Demographic topic. You'll find the child's z-scores under the Child Anthropometry topic.
Click on the + sign by a variable to add it to your data extract. Click on the variable name to get details about it, including skip patterns (under "Universe") and the exact survey text.
Click on "Select samples" to limit the information to just the Indian surveys.
Liz Boyle
Professor Elizabeth Boyle
Sociology & Law, University of Minnesota, USA
Principal Investigator, IPUMS-DHS
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
