Tests for the Gamma Distribution with Estimated Shape Parameters

Abstract

It is well known that the distributions of the goodness -of-fit statistics W squared, U squared, A squared do not depend on location and scale parameters even when these parameters must be estimated. It has generally been assumed, however, that when shape parameters must be estimated the null distributions of these statistics would depend too severely on the unknown parameters to permit their use in practice. Exact asymptotic distributions of these statistics are presented for the two parameter gamma family distributions. Critical points are given in tables constructed so as to avoid any need for extrapolation. The results presented show that the tests can be expected to be useful in practice.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 14, 1989
Accession Number
ADA205829

Entities

People

  • M. A. Stephens
  • R. A. Lockhart

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Classification
  • Covariance
  • Data Science
  • Distribution Functions
  • Eigenvalues
  • Eigenvectors
  • Extrapolation
  • Gaussian Processes
  • Information Science
  • Normal Distribution
  • Numerical Analysis
  • Random Variables
  • Security
  • Statistics
  • Stochastic Processes
  • United States

Fields of Study

  • Mathematics

Readers

  • Regression Analysis.