Theme-2-4-Application of LP3 distribution to censored samples.

Abstract

The effects of the type-1 censoring on the maximum likelihood estimators based on samples drawn from the Log Pearson Type-3 (LP3) distribution were analyzed in this study. For this purpose, all the equations needed in obtaining the maximum likelihood estimators and their asymptotic variances-covariances derived. Fran Monte Carlo experiments, it was found that censoring may reduce the bias in estimating the T-year event but increases its variance. It was also found that the type-1 censoring can be effectively used in dealing with samples containing outliers.