Goodness-of-Fit Tests for the Type-I Extreme-Value and Two-Parameter Weibull211 Distributions with Unknown Parameters Estimated by Graphical Plotting Techniques. 211 Part 1: Critical Values

摘要

The objective of this study is to determine the critical values of the Cramer-von211u001eMises (C-M) and Anderson-Darling (A-D) statistics for goodness-of-fit tests for 211u001ethe Type-1 extreme-value and two-parameter Weibull distributions when the 211u001epopulation parameters are estimated from a complete sample by graphical plotting 211u001etechniques. Three kinds of graphical-plotting technique i.e., the median ranks, 211u001emean ranks, and symmetrical sample cumulative distribution (symmetrical ranks), 211u001eare combined with the least-squares method on extreme-value and Weibull 211u001eprobability paper to estimate the parameters. Monte Carlo simulation is used to 211u001ecalculate the critical values of the C-M and A-D statistics, in which 1,000,000 211u001esets of complete samples are generated ten times for each sample size of 3(1)20, 211u001e25(5)50, and 60(10)100. The critical values are discussed and tabulated for 211u001epractical use.