Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Bug in stsplit and stptime - or me ?
From
[email protected] (Yulia Marchenko, StataCorp LP)
To
[email protected]
Subject
Re: st: Bug in stsplit and stptime - or me ?
Date
Mon, 10 Oct 2011 14:15:18 -0500
Jesper Lindhardsen <[email protected]> used -stset- to set his
data, issued some -st- commands, and then changed the -st- settings by
using -stset- again. That would be fine except that, in the second
-stset- command, Jesper used system variables created by the previous
-stset- command such as _t, _t0, _d, etc.
You must not do that. You can re-stset if you wish, but you must not
use variables _t, _t0, _d, etc. We will modify -stset- to issue an
error message when system variables are used.
As a side note, Jesper used the -enter()- and -origin()- options
interchangeably in his code. Although in his example it led to the
same results, this will not be true in general. It is important to
remember that the -origin()- option specifies the onset of risk of
subjects and, thus, redefines the analysis time. The -enter()- option
specifies when subjects enter a study which may be after they have
already been at risk of a failure. The distinction between these
options is crucial for correct declaration of your survival data.
-- Yulia
[email protected]
*
* 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/