A SEMI-PARAMETRIC ESTIMATION OF COPULA MODELS BASED ON MOMENTS METHOD UNDER RIGHT CENSORING

A SEMI-PARAMETRIC ESTIMATION OF COPULA MODELS BASED ON MOMENTS METHOD UNDER RIGHT CENSORING

N. Idiou, F. Benatia, B. Brahimi

[PDF]

Abstract

Based on the classical estimation method of moments, a new copula esti- mator was proposed for censored bivariate data. As theoretical results, general formulas were proved with analytical forms of the obtained estimators. Taking into account Lopez and Saint-Pierre's(2012)[19], Gribkova and Lopez's (2015)[10] results, the asymptotic normality of the empirical survival copula was established. The dependence structure between the bivariate survival times was modeled under the assumption that the under- lying copula is Archimedean. Accounting for various censoring patterns (singly or doubly censored), a simulation study was performed enlighten the behavior of the procedure es- timation method, shown the e ciency and robustness of the new estimator proposed.

Keywords

Archimedean copulas models, Bivariate censoring, Moment estimator, Sur- vival copula, right censored data.