raoul reulen ha scritto:
Dear All
I have a query about competing risks and Cox regression. When
calculating cumulative incidence I understand it is important to
account for competing risks (using, for example, Enzo Coviello's
stcompet). For example, death is a competing risks for recurrence of a
cancer. But what if I am interested in potential explanatory factors
of cancer recurrence (e.g. age at diagnosis)? Would a Cox regression
analysis give me the correct answers or would I have to use the newly
implemented command stcrreg? Both models obviously work, but how
should I interpret the results?
Hi Raoul,
I believe you can find useful to this aim the command -stcompadj-
available in the SSC Archive.
Note that as ancillary file there is a presentation at the last Italian
SUG with some reply to your question.
Best wishes.
Enzo
Thanks.
Raoul
*
* 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/
--
Enzo Coviello
Epidemiology Unit ASL BT
via Fornaci, 201 - 70031 ANDRIA (BT)
Italy
tel
mobile 347 5016016
^^^^
Home
via Imbriani, 186 - 70055 MINERVINO MURGE (BA)
tel +39 0883 695055
*
* 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/
