Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Survival Analysis Issue


From   "Yaseen Ghulam" <[email protected]>
To   [email protected]
Subject   st: Survival Analysis Issue
Date   Wed, 24 Nov 2004 16:27:01 -0000

Dear Stata Users,
I am using stata routines to do survival analysis. I am interested estimate expected and median survival time.
By following Professor Stephen P. Jenkins notes and codes and using duration data I got the following results.

* Weibull model, PH, coeffients
streg drug age, dist(weibull) nolog nohr
predict xb, xb
su xb
di "WEIBULL MODEL"
* median duration for each person in sample
ge mediand = (ln(2)*exp(-xb))^(1/e(aux_p))
* expected (mean) duration for each person in sample
ge meand = exp(-xb/e(aux_p))*exp(lngamma(1+1/e(aux_p)))

Variable |       Obs        Mean    Std. Dev.       Min        Max
-------------+--------------------------------------------------------
          _d |        22    .8181818     .394771          0          1
         _t0 |        22           0           0          0          0
          _t |        22    12.77273    8.123639          1         32
     mediand |  22     13.0186    3.276344   8.531759    19.7746
       meand |  22    14.97909    3.769734   9.816569   22.75249
This makes sense to me because median and mean duration min and max values are within the range of actual max value.

But when I am usually exactly these codes on my data I am getting some values which are quite extreme. Am I making some mistake?

Here is the command I am using and results I am getting.
streg   variable list.........., dist(weibull) nolog nohr
predict xb, xb
di "WEIBULL MODEL"
* median duration for each person in sample
ge mediand = (ln(2)*exp(-xb))^(1/e(aux_p))
* expected (mean) duration for each person in sample
ge meand = exp(-xb/e(aux_p))*exp(lngamma(1+1/e(aux_p)))


    Variable |       Obs        Mean    Std. Dev.       Min        Max
-------------+--------------------------------------------------------
          _d |    269512    .0049831     .070415          0          1
         _t0 |    269512    10.33649    6.762769          0   28.32854
          _t |    269512    10.41994    6.762693   .0629706   28.41342
     mediand | 269512    40.65339     63.9578    .142106   1261.704
       meand | 269512    69.90463    109.9772   .2443553   2169.535




Yaseen Ghulam
Senior Lecturer in Banking and Finance
Department of Economics 
Portsmouth Business School
University of Portsmouth, Richmond Building
Portland Street, Portsmouth

* * 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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index