A Cramer-Rao type inequality for estimating a hazard with censoring

Catherine Huber-Carol (1)

1 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5

Two very active areas of statistical research are non-parametric function estimation and analysis of censored survival data. A minimax asymptotic rate of convergence for the estimation of a hazard is obtained, in the presence of random right censoring using the link between the Kullback–Leibler distance of two probabilities and a weighted Lp-type distance between their corresponding hazards.

Mots clés: Censoring; estimation; hazard rate; lower bounds.

Domaines: Statistiques [math.ST]

Catherine Huber-Carol. A Cramer-Rao type inequality for estimating a hazard with censoring. 2017 Conference Lifetime Data Science on Precision Medicine and Risk Analysis with Lifetime Data, Mei-Cheng Wang, Johns Hopkins University, May 2017, Storrs CT, United States. ⟨hal-01445206⟩