I never used survival analysis in a submitted or published paper, but I am pretty confident that a translation of the help should sound like this:
-time0()- (please note the use of minus around the command, and not an underscore) records the enter times for subjects who enter in the risk pool, die and then resurrect to enter again in the risk pool.
I guess that the useful thing for you is -origin()-
Nicola
At 02.33 30/12/2006 -0500, you wrote:
>Date: Fri, 29 Dec 2006 17:23:16 -0200
>From: "josemaria" <[email protected]>
>Subject:
>
>Dear statalisters:
> the manuals and the help for stset say that _time0 ()_ "is rarely
>specified... and should be used exclusively with multiple-record data, and
>even then it should be considered whether _origin()_ or _enter()_ would be
>more appropriate". However, the book An Introduction to Survival Analysis
>Using Stata, by Cleves, Gould & Gutierrez, first edition, on pages 92-94,
>shows the use of _time0()_ for left truncation (delayed entry) and not for
>multiple-record data. Can the _stcox_ command be used to complete the
>analysis ? I have a data set with a situation alike the example (subjets
>enter at several different times to form the risk sets) and I am at lost
>with the options for stset.
> Thank for the help,
>Jos� Maria
*
* 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/
