IMPROVED PERCENTILE ESTIMATION FOR THE 2-PARAMETER WEIBULL DISTRIBUTION

This paper presents an improvement of a technique recently published t o estimate the parameters of the two-parameter Weibull distribution. A simple percentile method is used to estimate the two parameters. Comp uter simulation is employed to compare the proposed method with the ma ximum likelihood estimation and graphical methods results. A set of fr equently-used and newer expressions for estimating the cumulative dens ity are examined. Comparisons are made with both complete and censored data. The primary advantage of the method is its computational simpli city. Results indicate that with respect to Mean Square Error and esti mation of the characteristic value with complete data, the percentile method cannot outperform the maximum likelihood method, although diffe rences are minor in many instances. However, with censored data, impro vements over the maximum likelihood are observed. When the shape param eter is estimated, the percentile method is quite competitive with tha t of maximum likelihood for both complete and censored data under a va riety of conditions.