The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Biomarkers » Anemia variable in MR (Men's Anemia)
Anemia variable in MR [message #18916] Tue, 17 March 2020 17:50 Go to next message
nagar002 is currently offline  nagar002
Messages: 9
Registered: April 2018
Member
Hi All,

I am working with men's Anemia variable for many DHS (across countries and time) pooled together. I have the following questions. Any help is much appreciated.

1. There are many men in the men's recode file who have missing haemoglobin information. As I understand from the description in the country report, the selection of men for interview and for anemia testing was random and the low response rate for men's anemia is not the result of some sample selection criterion. Is that correct?

2. If regression analysis (with anemia as dependent variable) is being done separately for men and women in a couple {i.e., subsample of men (from MR file) and women (from IR file) who can be matched to form a couple}, what sample weights should be used?

Thank you!
Re: Anemia variable in MR [message #18925 is a reply to message #18916] Fri, 20 March 2020 11:31 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
A response from data processing specialist, Bert Themme:
Quote:

The selection criteria for men's anemia testing in surveys is often a subset for all households. Thus for example every second or third household is selected for men's anemia testing. In this case, the selection is a random sample of every second or third household in the cluster (randomly selected before fieldwork in the cluster starts), which causes the low overall response.

When we produce couple tables, we always use the man's weight.
Re: Anemia variable in MR [message #18984 is a reply to message #18925] Mon, 30 March 2020 18:51 Go to previous messageGo to next message
nagar002 is currently offline  nagar002
Messages: 9
Registered: April 2018
Member
Many thanks you for your help.
Re: Anemia variable in MR [message #19336 is a reply to message #18925] Tue, 02 June 2020 00:46 Go to previous messageGo to next message
nagar002 is currently offline  nagar002
Messages: 9
Registered: April 2018
Member
Hi all,

My analysis is for India 2005 and India 2015. I am running a regression with anemia as the dependent variable for the sample of men and women who can be matched to each other (i.e. from the CR file) and have non-missing anemia information for both husband and the wife (to be precise, the regressions are run separately for these men and women). Then,

1) Is this sample likely to be a selected sample of men and women, or is it safe to say that it is a random sample for both men and women?


2) Since this regression is for a sub-sample of men (women) who have non-missing anemia information AND must be matched to wives (husbands) with non-missing anemia information, I am wondering if mv005 is the correct weight to use in the two separate regressions for husbands and wives, and is there any adjustment required to the weight variable. I ask this because the analysis is not for the universe of men who were surveyed (and found in the MR files), but only those who have anemia information available in the PR file and who have wives with non-missing anemia information in the CR file. The results of my regressions differ substantially based on whether I use man's weights or not (mv005 in CR file). I am wondering if in this case weights should not be used at all.

Many thanks for any help. Much appreciated.


Re: Anemia variable in MR [message #19341 is a reply to message #19336] Tue, 02 June 2020 10:12 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User, a response from Dr. Tom Pullum:
Quote:

You should always use weights, and your models should also make the svyset and svy adjustment for clusters and strata (svyset and svy are described in other postings). In the CR file we recommend that you use mv005. You should get a big difference between using no weights and using mv005. The difference between using mv005 and v005 should be small, but we still recommend using mv005 rather than v005 because nonresponse is usually worse for men than for women and the weights include adjustments for nonresponse.

The IR and MR files are representative of women and men, respectively (subject to the criteria for eligibility, i.e. age and de facto residency status). The CR file is representative of couples but not of all women or all men. You can compare the anemia for women in the IR file vs women in the CR file to get at the selection bias for women. Similarly for men. You can also compare with the anemia values in the PR file.

Re: Anemia variable in MR [message #19352 is a reply to message #19341] Wed, 03 June 2020 23:06 Go to previous message
nagar002 is currently offline  nagar002
Messages: 9
Registered: April 2018
Member
Thank you very much, Tom.
Previous Topic: BMI FOR AGE
Next Topic: BMI
Goto Forum:
  


Current Time: Thu Mar 28 19:45:03 Coordinated Universal Time 2024