. qui sysuse cancer, clear
. qui stset studytime, failure(died==1)
. sts list, at(0 15) failure by(drug)
failure _d: died == 1
analysis time _t: studytime
Beg. Failure Std.
Time Total Fail Function Error [95% Conf. Int.]
-------------------------------------------------------------------------------
drug=1
0 0 0 0.0000 . . .
15 4 16 0.8313 0.0876 0.6338 0.9572
drug=2
0 0 0 0.0000 . . .
15 7 3 0.2552 0.1310 0.0874 0.6129
drug=3
0 0 0 0.0000 . . .
15 13 2 0.1429 0.0935 0.0378 0.4606
-------------------------------------------------------------------------------
Note: Failure function is calculated over full data and evaluated at
indicated times; it is not calculated from aggregates shown at left.
However, the estimates saved in r() after -sts list- do not help me:
. return list
scalars:
r(N) = 10
r(sum_w) = 10
r(mean) = 35.5
r(Var) = 9.166666666666666
r(sd) = 3.027650354097492
r(min) = 31
r(max) = 40
r(sum) = 355
-sts generate- allows me to predict the failure function, but the
failure times in my dataset are random and I do not always have an
observation at each discrete time for which I want a prediction.
Is there a way to use -sts generate- to generate the failure function
values in a different dataset than that in which my data is stset?
Or, is there another way to capture the estimates I want so that they
are accessible to do-file code?
Hope someone can help ... thank you for your time!
Jacki
*
* 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/
