The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Kenya » COMPARING SIGNIFICANCE ACROSS SURVERY
COMPARING SIGNIFICANCE ACROSS SURVERY [message #12427] Mon, 15 May 2017 16:05 Go to next message
akwarae@gmail.com is currently offline  akwarae@gmail.com
Messages: 13
Registered: August 2014
Member
I am trying to compare contraceptive use, whether there was a significant change across survey years, for instance, comparing 1993 versus 2003 etc.
I have appended all DHS surveys from 1993-2003 and I used the following STATA code.

test [DHS_1993_modern]1.age=[DHS_2003_modern]1.age

Kindly advice if this is the right way and how I can make CI graphs for the output.


N.B:// I would like to test separately for 15-19 year old females and 20-24 year olds separately.

Many thanks.

Report message to a moderator

Re: COMPARING SIGNIFICANCE ACROSS SURVERY [message #12432 is a reply to message #12427] Tue, 16 May 2017 13:16 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3230
Registered: February 2013
Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum:


Yes, the way you have set this up will work. You can do separate tests for age interval 15-19 and age interval 20-24 (v013=1 or =2). I cannot advise you on graphing procedures beyond saying that both equiplot and forest plots are good for comparing confidence intervals. You will have to look them up and download ado files. Equiplot is good for a small number of comparisons and forest plots are better for lots of comparisons. You will see examples of these techniques in recent Analytical Studies and Comparative Reports on the DHS website.

Report message to a moderator

Re: COMPARING SIGNIFICANCE ACROSS SURVERY [message #12433 is a reply to message #12432] Tue, 16 May 2017 13:48 Go to previous message
akwarae@gmail.com is currently offline  akwarae@gmail.com
Messages: 13
Registered: August 2014
Member
Many thanks for the response.

Report message to a moderator

Previous Topic: Missing Data in 2014 Survey- V215, unmet need
Next Topic: Health Insurance Data.
Goto Forum:
  

[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Mon Nov 3 22:18:16 Coordinated Universal Time 2025
.:: Contact :: Home :: Privacy Policy ::.

Powered by: FUDforum 3.0.9.
Copyright ©2001-2018 FUDforum Bulletin Board Software