Merging data sets [message #24249] |
Tue, 29 March 2022 10:43 ![Go to next message Go to next message](/theme/default/images/down.png) |
Suja
Messages: 2 Registered: March 2022
|
Member |
|
|
I would like to know what is the correct unique identification variable for merging NPPR and NPHR datasets. Are V001 and V002 sufficient or do I need to take V003 as well? similarly please give suggestions on merging NPPR with NPIR or NPMR datasets. Thank you.
[Updated on: Tue, 29 March 2022 10:44] Report message to a moderator
|
|
|
Re: Merging data sets [message #24301 is a reply to message #24249] |
Fri, 15 April 2022 16:00 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
admin
Messages: 50 Registered: November 2012
|
Senior Member Administrator |
|
|
Following is response from DHS Research & Data Analysis Director, Tom Pullum:
There is almost never a reason to merge the PR and HR files. The PR file is a long version of the HR file and the HR file is a wide version of the PR file. The strictly household-level data is coded onto each person-level record in the PR file.
There are exceptions, however. Please identify the specific survey and say why you want to do this merge and we will try to help.
We now have repositories of code written in Stata and SPSS available on Github. Please reference these code repositories as a resource for code for matching or calculating DHS indicators. The code repositories can be found at:
https://github.com/DHSProgram/DHS-Indicators-Stata
https://github.com/DHSProgram/DHS-Indicators-SPSS
|
|
|