The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Other countries » mv852a in Zimbabwe 2015 men's recode (anomalous data)
mv852a in Zimbabwe 2015 men's recode [message #25786] Fri, 09 December 2022 06:26 Go to next message
Emma Slaymaker is currently offline  Emma Slaymaker
Messages: 2
Registered: December 2022
Member
Hello,

I am using the men's recode from Zimbabwe 2015 for a comparative analysis and am getting some anomalous results based on responses to mv852a, mv852b and mv852c.
There are no responses in these three variables coded in the 400s for "years".
This is unusual and seems unlikely because it suggests that all the reported partners have been acquired recently- there are a few where a number of months greater that 12 has been recorded but most partners are recorded as new in the last year, including some spouses. For example, a cross tabulation of mv852a and mv767a shows that 2552 of the 4235 partnerships with spouses are reported as having started in the last year, which is extremely high. I think all the "year" answers have been dropped into the 300s instead of the 400s - is there a way to check?
Thanks,
Emma
Re: mv852a in Zimbabwe 2015 men's recode [message #25809 is a reply to message #25786] Tue, 13 December 2022 16:30 Go to previous messageGo to next message
Janet-DHS is currently offline  Janet-DHS
Messages: 720
Registered: April 2022
Senior Member
Following is a response from DHS staff member Tom Pullum:

Good call, Emma, You are right. Other evidence comes from a comparison with the 2010-11 ZW survey, in which the bulk of the values for mv852 a-c have first digit 4, for years. There is a coding error for question 420 in the Men's questionnaire. The questionnaire shows the usual 4 categories, but the data capture program only has the following 3 categories:

Days ago 1
Months ago 2
Years ago 3

Thus the 300 series of codes should be 400s, and the 200 series of codes should be 300s in the recode file. This doesn't appear to affect the women's data or question 415, just question 420. (Response from Trevor Croft and Tom Pullum)
Re: mv852a in Zimbabwe 2015 men's recode [message #25825 is a reply to message #25809] Thu, 15 December 2022 09:29 Go to previous messageGo to next message
Emma Slaymaker is currently offline  Emma Slaymaker
Messages: 2
Registered: December 2022
Member
Thank you, that's really helpful. I can leave them out the analysis with a clear conscience now!
Re: mv852a in Zimbabwe 2015 men's recode [message #25835 is a reply to message #25825] Fri, 16 December 2022 09:56 Go to previous message
paul bennell is currently offline  paul bennell
Messages: 1
Registered: December 2022
Member
Dear Emma

Please could you explain to me the difference between the estimates for 'educational attainment for female household population' and 'educational attainment for female household members'?

I am working as a consultant for the World Bank/Global Partnership for Education.

Best wishes

Paul Bennell
Previous Topic: District BPS code across the waves in Indonesia
Next Topic: Sierra Leone 2017 MICS6
Goto Forum:
  


Current Time: Sun May 26 17:52:51 Coordinated Universal Time 2024