The DHS Program User Forum: India » District level Individual panel data

Home » Countries » India » District level Individual panel data

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

District level Individual panel data [message #14967]

Tue, 22 May 2018 12:23

anirban.chattopadhyaya@gm is currently offline

anirban.chattopadhyaya@gm
Messages: 4
Registered: May 2018

Member

Hi,

I am trying to create panel dataset at individual across all 4 NFHS rounds.
I have encountered certain issues as I am going over the datasets.
1. For the 1st round, birth records and children level data don't have district level identifiers.
2. Recoded Individual dataset does not have district level identifier either. But the raw individual dataset has. But on trying to merge using "caseid" to locate common units, the match result is 0.

Help will be appreciated.

Report message to a moderator

Re: District level Individual panel data [message #14976 is a reply to message #14967]

Wed, 23 May 2018 07:49

Bridgette-DHS
Messages: 3199
Registered: February 2013

Senior Member

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

Are you trying to link individuals across surveys? That would be the normal implication of the term "panel". This cannot be done. Probably no one has appeared in more than one round of the NFHS, and even if someone has appeared more than once, it would be impossible to link the separate appearances. The individual id code (caseid) normally consists of the state code, cluster code, household code, and line number within the household. The only one of these that applies to successive surveys is the state code.

Report message to a moderator

Re: District level Individual panel data [message #14979 is a reply to message #14976]

Wed, 23 May 2018 08:02

anirban.chattopadhyaya@gm
Messages: 4
Registered: May 2018

Member

Thank you for the reply.

No, I am not trying to link the same individuals across different rounds. What I am trying to create pseudo-panel dataset at district levels(say by taking a mean, median, etc.).

To ask the question on caseid more specifically, how can one match observations amongst the 'individual raw' and 'individual recoded' from NFHS 1?

Report message to a moderator

Re: District level Individual panel data [message #14980 is a reply to message #14979]

Wed, 23 May 2018 09:13

Bridgette-DHS
Messages: 3199
Registered: February 2013

Senior Member

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

For NFHS-1 I see files IAIR23FL.dta and IAPR23FL.dta (the Stata versions). These are the recode files for individual women and individuals in the households. I don't know of any "raw" data files. Perhaps you have access to something I don't know about. What files are you using?

Report message to a moderator

Re: District level Individual panel data [message #14983 is a reply to message #14980]

Wed, 23 May 2018 09:26

anirban.chattopadhyaya@gm
Messages: 4
Registered: May 2018

Member

I am referring to IAIR23DT(.dta) and IAIQ21DT(.dta) where in the directory they are mentioned as Individual Recode and Individual Raw respectively.

Report message to a moderator

Re: District level Individual panel data [message #15007 is a reply to message #14983]

Thu, 24 May 2018 17:49

Bridgette-DHS
Messages: 3199
Registered: February 2013

Senior Member

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

You are right--our data processing archives for India include "raw" data files for NFHS-1. However, (1) they are not user-friendly (we in the analysis group never touch those files) and (2) they would not contain more information about geography than is in the recoded files. What you propose to do--tracking districts across the successive NFHS rounds--sounds interesting, but I don't see how we can help you with it.

Report message to a moderator

Re: District level Individual panel data [message #15074 is a reply to message #14967]

Wed, 30 May 2018 09:21

boyle014
Messages: 78
Registered: December 2015
Location: Minneapolis

Senior Member

IPUMS-DHS includes harmonized geography across all the India surveys.

If you use IPUMS-DHS, I'd recommend clicking on "Select Samples" to limit the interface to just the India surveys. The Indian integrated geography variable is GEO_IA1992_2015. You will find it under Topics -> Geography -> Integrated Geography.

Since you've started with the regular DHS files, you'll probably want to change the default to see the original DHS variable names in IPUMS-DHS. This option is in the upper right corner of the variable discovery screen:

index.php?t=getfile&id=888&private=0

Good luck with your research.

Attachment: Screen Shot 2018-05-30 at 8.17.44 AM.jpg
(Size: 14.01KB, Downloaded 1326 times)

Professor Elizabeth Boyle
Sociology & Law, University of Minnesota, USA
Principal Investigator, IPUMS-DHS

Report message to a moderator

Previous Topic:	Occupation Codes (NFHS - 4 India)
Next Topic:	Malaria

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Sun Nov 24 19:01:02 Coordinated Universal Time 2024