The DHS Program User Forum: General

Home » Topics » General » Marriage History

Show: Today's Messages :: Show Polls :: Message Navigator

Marriage History [message #2909]

Tue, 09 September 2014 07:09

Lorretta
Messages: 8
Registered: August 2013
Location: Nigeria

Member

I am conducting a study that aims to estimate the risk of divorce and separation in sub-Saharan Africa (Cameroon, Ghana, Nigeria, Kenya, Uganda, Tanzania). I have not seen any variable that captures time of marital dissolution in these countries. I need help on how to estimate the risk using survival analysis in the absence of complete marital history.

Lorretta

Report message to a moderator

Re: Marriage History [message #2912 is a reply to message #2909]

Tue, 09 September 2014 10:37

Trevor-DHS
Messages: 805
Registered: January 2013

Senior Member

Unfortunately the time of dissolution of marriage is not collected in the DHS surveys. I can't think of a way of using survival analysis for what you want to do with the data available. Sorry.

Report message to a moderator

Re: Marriage History [message #2913 is a reply to message #2909]

Tue, 09 September 2014 10:38

user-rhs
Messages: 132
Registered: December 2013

Senior Member

Loretta,
This is a tough one. The short answer is: there is no good way for this using DHS. Information on marital status in the 5+ yrs preceding interview is captured in the reproductive calendar (VCAL) variable column 3 (ref: http://dhsprogram.com/pubs/pdf/DHSG4/Recode6_DHS_22March2013 _DHSG4.pdf, p.98), but the information is very limited and the time frame is quite short. I don't know much about marriage in W. / E. Africa, but I imagine divorce rates are lower than in the U.S. or Europe, so that may present additional challenges to you if the number of observations for whom marriage has been dissolved is low. Maybe if you can use a combination of age at first marriage, current age, VCAL_3, and marital status to model survival of marriage (the idea is that if the difference in age at first marriage is within 5 yrs of interview, you might have "complete" marital history for those people). Even this has its problems and you will have lots of right-censoring in your data.

The WB's living standards surveys may have info on marital hx. I think some of them might even be panel.

HTH,
RHS

Report message to a moderator

Re: Marriage History [message #2914 is a reply to message #2913]

Tue, 09 September 2014 10:58

Trevor-DHS
Messages: 805
Registered: January 2013

Senior Member

While RHS is correct that some data can be found in vcal_3, they are limited to the last 5 years as he says, and, for the most part (with a couple of exceptions), these data have not been collected in the more recent surveys.

Report message to a moderator

Re: Marriage History [message #2916 is a reply to message #2914]

Tue, 09 September 2014 12:00

Lorretta
Messages: 8
Registered: August 2013
Location: Nigeria

Member

Thanks RHS for the useful information. Trevor is right, I have checked the datasets I have, there is no vcal_3 in the recent surveys. I will check WB.

Lorretta

Report message to a moderator

Previous Topic:	What does a ".a" response indicate?
Next Topic:	Female Genital Cutting data - Nigeria 2008

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Wed Jan 15 04:16:14 Coordinated Universal Time 2025