Shawn's question was on mortality. If death from competing causes is
handled as censored, Cox will not give the right answer. When a subject is
censored from analysis, he or she is still modeled as being at risk of the
event of interest. However, if the patient died, he or she will not be at
risk of further events, and Cox normally produces an overestimate of
mortality.
I other words, how does the result of this method compare with the one
obtained with competing risks proportional hazards regression, the
competing risk equivalent of Cox regression.
Fine and Gray (1999 - J. of the Am Stat Association , 94, p. 496-509)
propose a proportional hazard model where the cumulative incidences are
compared. Actually the main advantage of the Fine and Gray's model is that
we can see and test the effect of each covariate on the cumulative
incidence curves and this could be different from the effects we estimate
in an usual Cox model.
