Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: survival analysis help


From   Steve Samuels <sjsamuels@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: survival analysis help
Date   Fri, 17 Feb 2012 22:35:28 -0500

Your problem is to define the survival time variable and the event indicator appropriately.  The manual entry for -stset- has many examples.

Briefly, 

time = 1) time to death on waiting list (if died of  on waiting list): event =1
     = 2) time to transplant (if transplanted ): event = 2
     = 3) time to end of observation still alive on waiting list when observations): event =3
     = 4) time to death of unrelated cause while on waiting list: event =4
     = 5) time to leaving the waiting list for other reasons: event =5 etc.

While you could  define event =0 for cases 2/5, I have found it useful to have a single variable that captures status at the end of followup for the outcome event.

Then: 

****************************
stset time, fail(event=1)
****************************

Steve
sjsamuels@gmail.com


On Feb 17, 2012, at 8:14 PM, Eugene DePasquale wrote:

Hello,

I am having difficulty with survival analysis with Stata and survival
on the transplant waiting list. There are 2 major possibilities (for
simplicity) - either death on the waiting list or transplantation.
Death is the event, while transplantation would be a censoring event
as I am interested in survival for those who are not transplanted.

event = 1 (death on waiting list) & event = 0 (alive on waiting list)

transplant = 1 (transplanted) & transplant = 0 (not transplanted)

txdate = date of transplant


I am not sure how to set this up appropriately - I have this below,
but I'm not sure how to incorporate the censoring.

stset time, fail(event) id(id)

Any help would be greatly appreciated.

Thanks,
Eugene
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index