Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Emilie Chary <emilie_chary@yahoo.fr> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: stptime person-time |
Date | Fri, 19 Feb 2010 15:57:55 +0000 (GMT) |
Hello, I am working on survival data. When I use stset and then stptime, my person-time results are huge numbers. Are they in days or years? It seems like I get the right incidence rates if I use per(365000). Here are the two lines of code I'm using: stset endfollowup, failure(fail) origin(time mdy(12,31,2002)) enter(time beginfollowup) id(idpatient) stptime, by(vaccinated) per(365000) at (0 365 731 1096 1461 1826 2196 2557) If I use per(1000), my rates are too small to be possible. And I need to have the right number of person-time in years. Thank you in advance, Emilie * * 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/