Unweighted least squares estimation of weibull parameters

摘要

This paper considers several unweighted least squares estimation of the parameters of a two-parameter Weibull distribution and compares the results with the maximum likelihood estimator. The methods are illustrated with a numerical example. Within various parameters and sample sizes explored, in the simulation study, the least squares estimation procedure for small n over maximum likelihood is recommended for estimating the Weibull parameters. The unweighted least squares method is especially recomended for small samples and when the v-data are generated by using ln