Proposes a partially parametric estimation of a survival function when
data may be both left and right censored. Assuming that the chance of
censoring is not related to the individual's survival time, the propo
sed estimator treats the uncensored observations non parametrically an
d uses parametic models for the censored observations. In this way, th
e results extend Klein et al.'s work (1990) to the doubly censored dat
a case. Shows some of the properties of the estimator when the correct
theoretical parametric model is selected.