The semiparametric efficiency bound of the mixed proportional hazard model is derived. The density factors in such a way that there exists a complete sufficient statistic for the individual heterogeneity. The efficient score is shown to be the difference between the score in the parametric direction and its conditional expectation given the sufficient statistic. Applying this result to the single-spell Weibull mixed proportional hazard model, it is shown that its information matrix is singular and there cannot exist any [square root]n-consistent estimator sequence. The information of the multi-spell Weibull mixed proportional hazard model is shown to be nonsingular in general. Copyright 1994 by The Review of Economic Studies Limited.

Many structural economics models are semiparametric ones in which the unknown nuisance functions are identified via non-parametric conditional moment restrictions with possibly non-nested or overlapping conditioning sets, and the finite dimensional parameters of interest are over-identified via unconditional moment restrictions involving the nuisance functions. In this article we characterize the semiparametric efficiency bound for this class of models. We show that semiparametric two-step optimally weighted GMM estimators achieve the efficiency bound, where the nuisance functions could be estimated via any consistent non-parametric methods in the first step. Regardless of whether the efficiency bound has a closed form expression or not, we provide easy-to-compute sieve-based optimal weight matrices that lead to asymptotically efficient two-step GMM estimators.