The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » India » which state does v101 equal to 37 represent in India data?
which state does v101 equal to 37 represent in India data? [message #27536] Thu, 31 August 2023 02:43 Go to next message
dcpathak is currently offline  dcpathak
Messages: 6
Registered: September 2022
Member
I am working with the latest DHS data for India (2019-21). I noticed that variables v101 and v024 have data for a 37th state (no name given) with 158 observations, while Tamil Nadu has only 64 observations. Tamil Nadu had 3239 observations for data of 2015-16. Why the number of observations has decreased for Tamil Nadu and Assam in the latest round? Should we drop v101==37?
Thanks in anticipation,
Durgesh
Re: which state does v101 equal to 37 represent in India data? [message #27553 is a reply to message #27536] Fri, 01 September 2023 12:09 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3043
Registered: February 2013
Senior Member
Following is a response from Senior DHS staff member, Tom Pullum:

v101 is state. It is an exact copy of v024. I will attach the label below. The codes go from 1 to 37 but for some reason code 26 is skipped, so there are only 36 distinct values, as there should be, because India has 36 states. I will also attach the unweighted number of cases in the IR or women's file in the NFHS-5. You refer to 158 or 64 observations, but you must be talking about the distribution of some variable that only applies to a small part of the population.
  • Attachment: V101.docx
    (Size: 14.36KB, Downloaded 81 times)
Re: which state does v101 equal to 37 represent in India data? [message #27560 is a reply to message #27553] Tue, 05 September 2023 02:44 Go to previous messageGo to next message
dcpathak is currently offline  dcpathak
Messages: 6
Registered: September 2022
Member
Thanks for your response.
I am using the Couples' recode file for NFHS-4 and NFHS-5. The NFHS-4 CR file has 63,696 observations, whereas the one for NFHS-5 has 57,693 observations. I could see that you are correct about code 26 being missed in the IR file of NFHS-5. If I count all cases included in the domestic violence module (v044==1), it comes to 72,320 observations in NFHS-5. The corresponding number is 79,729 observations for NFHS-4. The significantly large difference between relevant observations in IR and CR files for NFHS-5 makes me wonder if I am making some mistakes. I would appreciate it if you could put some light on it.
Regards,
Durgesh
Re: which state does v101 equal to 37 represent in India data? [message #27564 is a reply to message #27560] Tue, 05 September 2023 16:05 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3043
Registered: February 2013
Senior Member

Following is a response from Senior DHS staff member, Tom Pullum:

I haven't checked your numbers, but taking them as you gave them, the ratio of CR to IR cases (with the DV module) for NFHS-4 is 63696/79729 = .729. The corresponding ratio for NFHS-5 is 57693/72320 = .728. These ratios are almost exactly the same. In both surveys, apparently, about 17% of women who responded to the DV module did not get into the CR file. I can think of at least two reasons why a woman who responded to the DV module would not be in the CR file. The first is that the partner who is described in the DV module may be a former partner, not a current partner/spouse. You will see a distinction between a current and a former partner is made in the DV module. If you enter "tab v501 d104", for example, you will see that the DV module may be administered to women who are not currently in a union. Second, for a couple to be included in the CR file, the man and woman must list each other as the current partner. There may be cases in which a mutual match did not happen. You can easily identify which women did not get into the CR file by merging v001 v002 v003 in the CR file with v001 v002 v003 in the IR file, restricted to cases in which d104 (for example) is not NA.

Previous Topic: Change in age of women for domestic violence module
Next Topic: Family Structure
Goto Forum:
  


Current Time: Sun Apr 28 14:14:09 Coordinated Universal Time 2024