| Re: Uganda 2011 - spousal physical violence [message #12653 is a reply to message #12646] |
Wed, 28 June 2017 10:56   |
Liz-DHS
Messages: 1516
Registered: February 2013
|
Senior Member |
|
|
Dear User,
1) In the men's survey, question 909 in the survey (page 457 of the Uganda report) or label md112 in the data, the question/label reads: 'respondent ever physically hurt wife/partner when he was not hurting her'. Could you please confirm whether this should read: 'respondent ever physically hurt wife/partner when she was not hurting him' (since this would be in alignment with the women's questionnaire)? If not, could you please clarify what this is measuring?
Answer: Thank you for pointing this out. It should read 'respondent ever physically hurt wife/partner when she was not hurting him' as you have indicated.
2) Could you please clarify what 4: frequency in last 12 months missing for d105 variables is? Specifically, does this mean that violence occurred within the past 12 months but it is uncertain whether this was often or sometimes, OR does this mean violence occurred but it is uncertain whether this was often, sometimes or not in the last 12 months?
Answer: This is really part of a two part variable where in the questionnaire you have the question itself ex: Q1105a, then a second part indicating the frequency. In this case it means that in the collection of the data, the 2nd portion (frequency) was not recorded. May have been due to interviewer error. So in this case I would say it was your first choice "violence occurred within the past 12 months but it is uncertain whether this was often or sometimes"
Here is the CSPro code for the 1st variable in the series:
{ Physical violence }
box Q1105A1 => D105A; { push, shake, throw something }
1 => Q1105A2;
2 => 0;
=> Q1105A1;
endbox;
if Q1105A1 = 1 & Q1105A2 in notappl,missing then
D105A = 4
elseif Q1105A1 = 1 & Q603 = 1 then
D105A = 4
endif;
3)I am trying to create a variable for spousal physical violence in the past 12 months but am having trouble replicating the 24.2% figure in table 16.9.1 (page 256). Could you please provide information on how this was calculated? I have provided my Stata code below.
gen currentphysviol=1 if d105a==1|d105a==2|d105b==1|d105b==2|d105c==1|d105c==2|d105d= =1|d105d==2|d105e==1|d105e==2|d105f==1|d105f==2|d105j==1|d10 5j==2|d130a==1
replace currentphysviol=0 if currentphysviol==.&v044==1
tab currentphysviol [iweight=domesticviolenceweight]
Answer I will refer the 3rd part of your query to one of our experts.
Hope this helps.
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
