ASYMPTOTIC NORMALITY OF TRIMMED L-MOMENTS ESTIMATOR FOR ARCHIMEDEAN COPULAS

Abstract

In order to present a new estimation approach for multi-parameter distributions without a mean or for heavy tailed distributions, in which the L-moments method proposed by Gumbel, (1960), is invalid due to the absence of theoretical L-moments, Trimmed L-moments were first introduced by Elamir and Seheult (2003). In this paper, a new estimation method based on multi-parameter copulas' Trimmed L-moments is proposed with a simulation study. The consistency and the asymptotic normality of the new estimator also established.