A CLASS OF ESTIMATORS OF THE SURVIVAL FUNCTION FROM INTERVAL-CENSOREDDATA

A model of interval censorship of a failure time T is considered when there is only one inspection time Y. The observable data are n indepen dent copies of the pair (Y, delta), where delta = [T less than or equa l to Y]. We construct a class of self-consistent estimators of the sur vival function of T defined implicitly through two equations and show their strong consistency under certain conditions. The properties of t he nonparametric maximum likelihood estimator are also investigated.