The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Child Health » Survival analysis using Cox proportional hazard regression
Survival analysis using Cox proportional hazard regression [message #21635] Tue, 01 December 2020 17:36 Go to next message
Ugonna is currently offline  Ugonna
Messages: 13
Registered: June 2020
Member
Hello everyone,

I need to carry out survival analysis using Cox proportional hazard regression on the kr file of Nigeria DHS for my study on under-5 mortality.

I have identified that I need these variables for it:
b3 - date of birth of child
b5 - child is alive (survival status)
b7 - age at death in months
v008 - date of interview
b19 - age of child in months

Please how do I go about preparing the data for analysis?

-Do I need to reshape the data from wide to long? If I do, how do I do that please?

-I have combined 'caseid' and 'bidx' into one variable to generate a unique ID variable. Did I do the right thing here?

-Also how do I construct the time of death/time to event/time variable?

Will really appreciate your kind assistance.

Thank you.
Re: Survival analysis using Cox proportional hazard regression [message #21710 is a reply to message #21635] Fri, 11 December 2020 10:17 Go to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 2345
Registered: February 2013
Senior Member

Following is a response from DHS Research & Data Analysis Director, Tom Pullum:

The file preparation and Stata syntax for this kind of a model are outside the range of support that the DHS staff will provide. Hopefully another forum user will respond.

Previous Topic: EARLY CHILD DEVELOPMENT
Next Topic: Support for Education among child 36-59 month
Goto Forum:
  


Current Time: Sun Jul 25 06:27:01 Coordinated Universal Time 2021