The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Other countries » regions AJK and GB in PDHS (Pakistan DHS)
regions AJK and GB in PDHS (Pakistan DHS) [message #24819] Fri, 15 July 2022 22:43 Go to next message
chande is currently offline  chande
Messages: 12
Registered: March 2021
Member
I am looking for the impact of WASH on child malnutrition.
Is it possible to include Azad Jammu & Kashmir and Gilgit Baltistan regions from PDHS in my analysis?
Re: regions AJK and GB in PDHS (Pakistan DHS) [message #24850 is a reply to message #24819] Wed, 20 July 2022 16:36 Go to previous messageGo to next message
Janet-DHS is currently offline  Janet-DHS
Messages: 666
Registered: April 2022
Senior Member
Following is a response from DHS Research & Data Analysis Director, Tom Pullum:

Those two regions can be analyzed separately (an analysis for AJK and a separate analysis for GB) but you cannot pool them and you cannot pool them with the rest of Pakistan. In the IR file, for example, the usual sample weight, v005, is 0 for those regions. The correct weight variable for these two regions is sv005, and it is normalized to have a mean of 1 (or 1000000) in each of them. To repeat, you cannot pool these regions with each other or with the rest of the country. The government of Pakistan has been very clear about not wanting users to do that.
Re: regions AJK and GB in PDHS (Pakistan DHS) [message #27709 is a reply to message #24850] Sun, 24 September 2023 23:06 Go to previous messageGo to next message
owraza is currently offline  owraza
Messages: 36
Registered: December 2013
Location: Karachi, Pakistan
Member
What is the reason for not pooling these two regions? I do understand that pooling them in rest of Pakistan and doing comparison analysis with previous PDHS would be inappropriate, but what if that is not the objective? What if I'm interested in using only PDHS 17-18. Also, related to the same issue, how appropriate it would be to AJK and GB regions in geographically weighted regression analysis in which spatial weights are used and would I still need to use sampling weights?
Re: regions AJK and GB in PDHS (Pakistan DHS) [message #27732 is a reply to message #27709] Wed, 27 September 2023 09:28 Go to previous messageGo to next message
Janet-DHS is currently offline  Janet-DHS
Messages: 666
Registered: April 2022
Senior Member
Following is a response from DHS staff member, Tom Pullum:

The surveys are "owned" by the countries. The government of Pakistan, for political reasons, did not want to include AJK and GB in the national estimates, because these are disputed territories. We at DHS must respect that decision. If you want to include AJK and GB in a national estimate, you can do that, of course, but we will not facilitate that.
Re: regions AJK and GB in PDHS (Pakistan DHS) [message #27744 is a reply to message #27732] Wed, 27 September 2023 22:35 Go to previous message
owraza is currently offline  owraza
Messages: 36
Registered: December 2013
Location: Karachi, Pakistan
Member
Thanks.
Previous Topic: Need ethical review documents
Next Topic: Pakistan DHS 2012 district codes
Goto Forum:
  


Current Time: Fri Mar 29 09:00:33 Coordinated Universal Time 2024