Under left truncation, data are observed only when . Usually, the distribution function of the is the target of interest. In this paper, we study linear functionals of the nonparametric maximum likelihood estimator (MLE) of , the Lynden-Bell estimator . A useful representation of is derived which yields asymptotic normality under optimal moment conditions on the score function . No continuity assumption on is required. As a by-product, we obtain the distributional convergence of the Lynden-Bell empirical process on the whole real line.
View on arXiv