The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Other countries » Self-reported age of marriage variable
Self-reported age of marriage variable [message #10895] Sun, 02 October 2016 03:45 Go to previous message
christalUTS is currently offline  christalUTS
Messages: 2
Registered: September 2016
Member
Hello,

I am working on a project about marriage age in Africa. One of the countries I am analysing is Benin and using all years the standard DHS data sets are available for. The datasets are of the "STATA individual recode data sets".

When I plot the proportion of women who are married/cohabiting before they turn 16 years old (using self-reported age of marriage variable) against their birth year I find a strange pattern in the data. In particular, among women who are very young in a given survey (e.g. age <=20) these proportions are low, but when I use a later survey and look at the women of the same birth year these proportions are twice as large. I have attached the graphs and Stata code used to generate them.

Could you please let me know what could explain this pattern? Is it that very young women tend to under-report their married status, or is it that the very young women who agree to participate in the survey are somehow different (e.g. more emancipated and hence less likely to be married before turning 16 y.o).Or am I just using the data incorrectly? I would very much appreciate your advice.
  • Attachment: code2.do
    (Size: 0.99KB, Downloaded 378 times)
  • Attachment: Figure.docx
    (Size: 80.63KB, Downloaded 392 times)
 
Read Message
Read Message
Read Message
Read Message
Previous Topic: Guatemala 2014-2015 data
Next Topic: Philippines -Current and Former Marital Status
Goto Forum:
  


Current Time: Sun Apr 28 22:05:59 Coordinated Universal Time 2024