An extensive power evaluation of some tests for the inverse Gaussian distribution

Many applications of the Inverse Gaussian distribution, including numerous reliability and life testing results are presented in statistical literature. The paper studies the problem of using entropy tests to examine the goodness of fit of an Inverse Gaussian distribution with unknown parameters. So...

Full description

Saved in:
Bibliographic Details
Published in:Communications in statistics. Simulation and computation 2017-08, Vol.46 (7), p.5410-5422
Main Author: Alizadeh Noughabi, H.
Format: Article
Language:English
Subjects:
Computer simulation
Entropy
Entropy (Information theory)
Error analysis
Goodness of fit
Goodness of fit tests
Inverse Gaussian distribution
Inverse Gaussian probability distribution
Monte Carlo simulation
Statistical tests
Test power
Type I error
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many applications of the Inverse Gaussian distribution, including numerous reliability and life testing results are presented in statistical literature. The paper studies the problem of using entropy tests to examine the goodness of fit of an Inverse Gaussian distribution with unknown parameters. Some entropy tests based on different entropy estimates are proposed. Critical values of the test statistics for various sample sizes are obtained by Monte Carlo simulations. Type I error of the tests is investigated and then power values of the tests are compared with the competing tests against various alternatives. Finally, recommendations for the application of the tests in practice are presented.
ISSN:0361-0918
1532-4141
DOI:10.1080/03610918.2016.1157185