The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » General Data Questions » Migration data: number of visitors (Different number of visitors from two variables)
Migration data: number of visitors [message #25731] Thu, 01 December 2022 15:09 Go to next message
MG is currently offline  MG
Messages: 2
Registered: October 2022
I am trying to identify the migrants using the two following questions for Rwanda (2019-20):

1. years lived in place of residence (mv104 from men recode)
2. usual resident or visitor (mv135 from men recode)

If I tabulate both variables, I am getting different numbers for "visitors". mv135 has more observations in visitor category and mv104 has less in visitor category.

Why is this happening? I have the same issue with the women's file.
Re: Migration data: number of visitors [message #25750 is a reply to message #25731] Mon, 05 December 2022 08:41 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3061
Registered: February 2013
Senior Member

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

I see that there are 20 men who are classified as "visitor" on mv135 (mv135=2) and "always" on mv104 (mv104=95 rather than 96). This does appear to be an inconsistency. I would give priority to mv135, which is based on hv102 in the PR file. (I assume that that mv135 agrees with hv102, although I have not checked.) You should not over-write a standard variable, but I would use one or the other of the following (two lines in Stata) to make the corredtion:

gen mv104_original=mv104
replace mv104=95 if mv135==2


gen mv104r=mv104
replace mv104r=95 if mv135==2

Previous Topic: Choice of the right recode file
Next Topic: Calculating fixed and random effects
Goto Forum:

Current Time: Sat May 18 18:57:29 Coordinated Universal Time 2024