The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » HIV » How to use weights to analyse HIV data further
How to use weights to analyse HIV data further [message #184] Fri, 22 March 2013 09:50 Go to next message
muluneh is currently offline  muluneh
Messages: 1
Registered: March 2013
Location: Addis Ababa
Member
I have a project to re-analyse the 2011 Ethiopian DHS data just to know whether there is a difference in contraceptive use between HIV positive and negative Ethiopian women. How can I use variable weights to re-analyse this data?

Muluneh
Re: How to use weights to analyse HIV data further [message #200 is a reply to message #184] Mon, 25 March 2013 16:21 Go to previous messageGo to next message
lucyveh is currently offline  lucyveh
Messages: 2
Registered: March 2013
Location: Temporary London UK/ Per...
Member

Dear muluneh,
could you explain us more about the difference you mean so that we could help you?? is it a difference in contraceptive adherence between HIV+ women and HIV-?? or you want to describe the difference in contraceptive effects in these two groups?? please be more specific about your objective! we can assist you!


Yves Lucien HAKORIMANA;
Reproductive Health Specialist;
Tropical Diseases Specialist
Re: How to use weights to analyse HIV data further [message #292 is a reply to message #200] Wed, 10 April 2013 10:59 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3017
Registered: February 2013
Senior Member
You need to check the manual of the software you are using for guidelines on using weights. Weights in the DHS data are multiplied by 1,000,000, so to get the right figures, you need to always divide the weights you are using by 1,000,000.

For more information on using DHS data for analysis, please go to: http://www.measuredhs.com/data/Using-Datasets-for-Analysis.c fm.
Re: How to use weights to analyse HIV data further [message #307 is a reply to message #184] Sat, 13 April 2013 07:52 Go to previous messageGo to next message
myigzaw is currently offline  myigzaw
Messages: 2
Registered: April 2013
Location: Ethiopia
Member
The weighted numbers are less than the unweighted numbers in Ethiopian DHS data. Should we still use sample weights to further analyse the HIV data? Don't you think that the power is much lower in the weighted than the unweighted data to do a regresion analysis for example? I wonder if weihting is still invaluble to analyse HIV data further.
Re: How to use weights to analyse HIV data further [message #743 is a reply to message #307] Fri, 06 September 2013 07:51 Go to previous message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
For information about using WEIGHTS with DHS data, please refer to The Guide to DHS Statistics http://www.measuredhs.com/pubs/pdf/DHSG1/Guide_to_DHS_Statis tics_29Oct2012_DHSG1.pdf Beginning on page 12. Our Standard Recode Manual also has information on WEIGHT variables. http://www.measuredhs.com/pubs/pdf/DHSG4/Recode6_DHS_22March 2013_DHSG4.pdf

Thank you!
Previous Topic: Couples data
Next Topic: How to use Weights for HIV and Women data
Goto Forum:
  


Current Time: Thu Mar 28 14:48:00 Coordinated Universal Time 2024