Efficiency of Kimball's Linearized Maximum Likelihood Estimators for the Two Parameter Weibull and Extreme Value Distributions

Document Type : Original Article

Authors

Abstract

Asymptotic efficiencies, of Kimball's linearized maximum likelihood estimator β ̂ for the scale parameter of the Type I extreme value distribution are evaluated for Type II censored samples. The means and expected squared errors of β ̂ are compared with those of the best linear unbiased order statistic estimator and the asymptotic efficient linear order estimator based on a continuous weighting function for sample sizes n=10 and 20. Asymptotic efficiencies of an approximate maximum likelihood estimator α̂ for the location parameter α of the extreme value distribution are also evaluated.

Keywords