Home » Countries » Other countries » Namibia 2013, mental health descriptives for 50-64 year olds
| Namibia 2013, mental health descriptives for 50-64 year olds [message #28765] |
Wed, 06 March 2024 07:10  |
kyle_dack86
Messages: 1
Registered: March 2024
|
Member |
|
|
Hi there,
On page 272 of the Namibia DHS report there is a table describing mental health characteristics in women.
I can reproduce most of these descriptives, except for two unusual data points which are zero in the table:
The final line - 50-64 year olds;
Columns - "Average number of days felt little interest or pleasure in doing things in the past 2 weeks" and "Average number of days felt low in energy, been in a bad mood, or been sad all of the time in the past 2 weeks"
In the report these are both 0.0, but I find them to be 0.6 and 0.7.
In the mens' table I can replicate both of these data points using the same code. I checked a histogram and there are a significant number of women who report >0 days, so I am not sure how the 0.0 numbers were produced?
|
|
|
|
|
|
|
|
| Re: Namibia 2013, mental health descriptives for 50-64 year olds [message #28863 is a reply to message #28821] |
Tue, 19 March 2024 14:02  |
Janet-DHS
Messages: 938
Registered: April 2022
|
Senior Member |
|
|
Following is a response from DHS staff member, Tom Pullum:
On page 297 of the final report I see the following:
"20.1.3 Subsample for the Violence Module. The domestic violence module was implemented only in the subsample of households selected for the men's survey. Furthermore (as mentioned above), in keeping with ethical requirements, only one woman per household was selected for the module. A total of 2,226 women were successfully interviewed. Specially constructed 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."
This statement implies that the DV variables are in the CR file. However, after some checking, it appears that the statement should be revised, indeed reversed, to read "households selected for the men's survey" should be "households not selected for the men's survey".
In the PR file, the variable hv027 indicates whether the household was selected for the men's survey. I merged hv027 onto the IR file and then checked for the presence of d101a, one of the DV variables (see below). That merge confirms that the statement on page 297 is indeed the opposite of the actual design. Therefore, unfortunately, you cannot analyze the DV variables and the men's variables together. This is a situation we would like to avoid, but it's a typical design, based on fieldwork criteria, because it tends to equalize the length of time spent interviewing each household.
use "...NMPR61FL.DTA", clear
keep if hv117==1
keep hv001 hv002 hvidx hv027
rename hv001 cluster
rename hv002 hh
rename hvidx line
save temp.dta, replace
use "...NMIR61FL.DTA"
keep v001 v002 v003 d*
rename v001 cluster
rename v002 hh
rename v003 line
merge 1:1 cluster hh line using temp.dta
tab d101a hv027
[Updated on: Tue, 19 March 2024 14:04] Report message to a moderator |
|
|
|
Goto Forum:
Current Time: Wed Jan 29 17:01:51 Coordinated Universal Time 2025
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
