I think this is a bug, but have I have I done something stupid?
. webuse leukemia, clear
(Leukemia Remission Study)
. stset weeks , fail(relapse )
[output omitted]
. stcox treatment1 i.wbc3cat, nolog
failure _d: relapse
analysis time _t: weeks
Cox regression -- Breslow method for ties
No. of subjects = 42 Number of obs = 42
No. of failures = 30
Time at risk = 541
LR chi2(3) = 33.02
Log likelihood = -77.476905 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
_t | Haz. Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
treatment1 | .2834551 .1229874 -2.91 0.004 .1211042 .6634517
|
wbc3cat |
2 | 3.637825 2.201306 2.13 0.033 1.111134 11.91015
3 | 10.92214 7.088783 3.68 0.000 3.06093 38.97284
------------------------------------------------------------------------------
. estat phtest
too few variables specified
the current estimation results for cox have 4 equations so you must
specify 4 new variables, or
you can use the equation() option and specify one variable at a time
r(102);
If I use the preexisting indicators wbc2 and wbc3 (as in the example
in the manual) instead of the factor variable, or if I use -xi- then
estat phtest works.
Tim
[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/
