The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » India » N for DV module MFHS-5 (N for DV module MFHS-5)
N for DV module MFHS-5 [message #25063] Thu, 25 August 2022 19:57 Go to next message
behayes4 is currently offline  behayes4
Messages: 23
Registered: February 2020
Member
In the codebook, the N for the DV module reads as 72,056. However, the N in the data is 72,320. Has anyone identified the reason for this discrepancy?

There are also 420,149 women who were selected and not interviewed. This category is sizably larger compared to the 2015-2016 surveyed. There is no detail on this group. Who is included within this category>
Re: N for DV module MFHS-5 [message #25070 is a reply to message #25063] Fri, 26 August 2022 11:14 Go to previous messageGo to next message
fred.arnold@icf.com is currently offline  fred.arnold@icf.com
Messages: 79
Registered: May 2021
Senior Member
Information on the domestic violence sample selection and completed interviews is provided on Page 640 of the NFHS-5 national report (see below).

"In accordance with the World Health Organization's guidelines on the ethical collection of information on domestic violence, only one eligible woman per household was randomly selected for the module, and the module was not administered to eligible woman age 18-49 if privacy could not be obtained after at least three attempts during the survey. In total, 72,056 women completed the domestic violence module. Only 4 percent of women eligible for the domestic violence module could not be successfully interviewed with the module because privacy could not be obtained or for other reasons. Special weights were used to adjust for the selection of only one woman per household and to ensure that the domestic violence subsample was nationally representative."

Note that the age range for eligibility in NFHS-5 is 18-49, whereas it was 15-49 in NFHS-4. Tables 15.1, 15.4, and 15.5 in the NFHS-5 national report are all based on 72,056 women. The number of eligible women for the domestic violence module would have been much larger is women age 15-17 had been included in the base. Overall, 7.2% of de facto women age 15-49 in the household were age 15-17.

It is also important to note that in NFHS-5 the domestic violence module was included only in the "state module," which is a subsample of 15 percent of households. A similar procedure was used in NFHS-4.
Re: N for DV module MFHS-5 [message #25093 is a reply to message #25070] Tue, 30 August 2022 15:53 Go to previous messageGo to next message
behayes4 is currently offline  behayes4
Messages: 23
Registered: February 2020
Member
Thanks for your response! Even when I cross-tab age with the module variable, the numbers do not add up. According to this, there were 133 women aged 15 - 17 selected and who seemed to have been interviewed for the module. This does not add to the discrepancy of 264 between 72,056 in the codebook and 72,320 in the data.
Re: N for DV module MFHS-5 [message #25094 is a reply to message #25093] Tue, 30 August 2022 16:57 Go to previous message
fred.arnold@icf.com is currently offline  fred.arnold@icf.com
Messages: 79
Registered: May 2021
Senior Member
Although overall, 7.2% of de facto women age 15-49 in the household were age 15-17, this does not mean that 7.2 percent of all women in the household were age-eligible for the domestic violence questions. There should not have been ANY women age 15-17 who were selected for the DV questions, and no women in that age group should have been administered the DV questions under any circumstances. According to the filter question WQ1101, any woman who has not been selected for the household relations questions on the cover page of the Woman's Questionnaire skips the household relations questions and goes directly to the end of the interview. According to the filter question WQ1102, if privacy is not possible, the household relations questions are all skipped, and there is a skip to WQ1139, which asks for an explanation of why the domestic violence module was skipped. Those skip patterns should be automatic. It is possible that in a few cases a woman's age in household questionnaire was inaccurate and the woman may actually have been age 18 or older.
Previous Topic: District names for NFHS-1992-93
Next Topic: Utilization of ICDS services, India, NFHS-5
Goto Forum:
  


Current Time: Thu Apr 25 15:08:21 Coordinated Universal Time 2024