st: generating time for correlated competing events

[Enzo Coviello <enzo.coviello@alice.it>]

Dear Stata Users,

to simulate survival data of two independent 
competing risks following an exponential distribution we can type:

set obs 5000
g  time_ev1 = -1/ 0.2 * log(1-uniform())
g time_ev2 = -1/ 0.4 * log(1-uniform())
g time = min(time_ev1,time_ev2)
g byte fail = (time_ev1<time_ev2) + 2*(time_ev1>=time_ev2)

where 0.2 and 0.4 are the hazards we want simulate.

Now I need to simulate a competing event whose 
hazard is not independent from the hazard of the first event.
How can a new time variable be generated:

g time_ev3 =  ?


Thanks

Enzo



Enzo Coviello
Unit� di Epidemiologia e Statistica ASL BARI
Piazza V.  Emanuele 14 - 70054 Giovinazzo (Bari)
tel./fax +39 080 3357867
mobile 347 5016 016
home +39 0883 695055


*
*   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/