st: survival models for competing and recurrent events

[fernandez@wzb.eu]

Dear all,

I want to fit survival models for discrete time data with recurrent and
competing events. My dependent variable is the type of economic policy
reform (expansive or non-expansive) passed in a given country, which
occurs several times over the period covered by the study. In my analysis
of the literature, I have found separate discussions about how to treat
survival data for recurrent events and how to treat competing events. For
instance, the Stata manual Survival Analysis and Epidemiological Tables
mentions that the command –stcrreg– is appropriate to estimate
competing-risk models, but it cannot be used when you have multiple
failures (p. 196). Furthermore, that manual recommends using –stcox– when
dealing with multiple events, however it doesn't recommend it for multiple
and recurrent events. Is there any Stata program (or combination of
commands) to treat data with multiple and recurrent events?

Thanks for your consideration,

Juan



*
*   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/