Hi Enzo,
Thanks for your reply. So am I right that stcompet can handle (left)
truncated data as long as it is defined in stset?
For example, if I stset the data as you said:
.stset age_x, fail(fail==1) enter(time age_e)
and most persons become at risk at age 0, but a few people enter risk
and age 20, and thus have a delayed entry, then
the latter persons don't contribute to the cumulative incidence before
age 20? Is that right? Thanks a lot.
Raoul
2007/1/29, Enzo Coviello <[email protected]>:
At 21.17 29/01/2007, you wrote:
>Hi,
>
>I would like to calculate the complement of the Kaplan-Meier and the
>cumulative incidence in the presence of competing risks. However,
>several subjects in my cohort data are left truncated (delayed entry)
>so the number of subjects at risk actually increases first and then
>decreases. I first stset my data as:
>
>stset age_x, fail(fail) time0(age_e)
Hi Raoul,
you should declare in -stset- wich is the main event:
stset age_x, fail(fail==1) enter(time age_e)
where fail==1 marks the main event.
Then -stcompet- can be used without special syntax to estimate
cumulative incidence:
stcompet CumInc = ci, compet1(2)
where fail==2 corresponds to the competing event.
Enzo
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
