Accession Number : ADA138098

Title :   Modified Kolmogorov-Smirnov, Anderson-Darling and Cramer-Von Mises Tests for the Logistic Distribution with Unknown Location and Scale Parameters.

Descriptive Note : Master's thesis,

Corporate Author : AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH SCHOOL OF ENGINEERING

Personal Author(s) : Yoder,J D

PDF Url : ADA138098

Report Date : 16 Dec 1983

Pagination or Media Count : 108

Abstract : The method of maximum likelihood is used to determine invariant estimates of the unknown location and scale parameters of a sample from the Logistic distribution. The partial derivatives of the likelihood function can not be solved explicitly, therefore the Secant method is used to iteratively determine the roots of the partial derivatives. Using these estimates, modified Kolmogorov-Smirnov, Anderson-Darling and Cramer-von Mises statistics are calculated for a given sample. This procedure is repeated 5000 times for sample sizes of n= 5(5)30. The 80th, 85th, 90th, 95th and 99th percentiles of the distribution of each statistic, for each sample size, is then calculated. These values are then used to generate tables of critical values for the Logistic distribution with unknown location and scale parameters. A power comparison between the three tests is performed using samples from various distributions.

Descriptors :   *Statistical tests, Statistical analysis, *Logistics, Air Force equipment, Failure, Life cycles, Statistical distributions, Maximum likelihood estimation, Theses

Subject Categories : Statistics and Probability
      Undersea and Antisubmarine Warfare

Distribution Statement : APPROVED FOR PUBLIC RELEASE