INFERENCE AND PREDICTION FOR A GENERALIZED LOGISTIC DISTRIBUTION BASED ON THE kTH LOWER RECORDS

摘要

The minimum variance unbiased estimator, the maximum likelihood estimator and the Bayesian estimator for the parameter of the generalized logistic distribution are obtained based on kth lower record values. The Bayes estimators are obtain using both the symmetric squared error, squared log error loss function and the asymmetric LINEX and General Entropy loss functions and two new loss functions which we call Modified General Entropy (MGE) loss function and Kullback-Leibler divergence type loss function (KLD). Interval prediction for future kth upper record values is also presented from a Bayesian point of view. Numerical computations are given to illustrate these procedures.