A non-parametric estimator of the limiting distribution of bivariate extremes under censoring
Abstract
We propose an estimator of the limiting survival distribution function of bivariate extreme values, namely the bivariate relative excesses beyond a high threshold, under random right censoring. We assume that the distribution functions of the main variables as well as those of the censored variables are of Pareto-type. Under suitable assumptions, we prove the uniform convergence in probability of our estimator on compact sets. The performance of the estimator is illustrated by a simulation study. Finally, our methodology is applied to an insurance dataset.
Fields of Study & Subjects
Probability and Risk Models
Statistical Distribution Estimation and Applications
Statistical Methods and Inference
Publication details
- Journal / source
- HAL (Le Centre pour la Communication Scientifique Directe)
- Publication date
- 11 January 2026
- Language
- EN
- Document type
- Preprint