Ta. Gooley et al., Estimation of failure probabilities in the presence of competing risks: New representations of old estimators, STAT MED, 18(6), 1999, pp. 695-706
Citations number
20
Categorie Soggetti
General & Internal Medicine","Medical Research General Topics
A topic that has received attention in both the statistical and medical lit
erature is the estimation of the probability of failure for endpoints that
are subject to competing risks. Despite this, it is not uncommon to see the
complement of the Kaplan-Meier estimate used in this setting and interpret
ed as the probability of failure. If one desires an estimate that can be in
terpreted in this way, however, the cumulative incidence estimate is the ap
propriate tool to use in such situations. We believe the more commonly seen
representations of the Kaplan-Meier estimate and the cumulative incidence
estimate do not lend themselves to easy explanation and understanding of th
is interpretation. We present, therefore, a representation of each estimate
in a manner not ordinarily seen, each representation utilizing the concept
of censored observations being 'redistributed to the right.' We feel these
allow a mote intuitive understanding of each estimate and therefore an app
reciation of why the Kaplan-Meier method is inappropriate for estimation pu
rposes in the presence of competing risks, while the cumulative incidence e
stimate is appropriate. Copyright (C) 1999 John Wiley & Sons, Ltd.