Open Access
June, 1985 Efficiencies of Chi-Square and Likelihood Ratio Goodness-of-Fit Tests
M. P. Quine, J. Robinson
Ann. Statist. 13(2): 727-742 (June, 1985). DOI: 10.1214/aos/1176349550

Abstract

The classical problem of choice of number of classes in testing goodness of fit is considered for a class of alternatives, for the chi-square and likelihood ratio statistics. Pitman and Bahadur efficiencies are used to compare the two statistics and also to analyse the effect for each statistic of changing the number of classes for the case where the number of classes increases asymptotically with the number of observations. Overall, the results suggest that if the class of alternatives is suitably restricted the number of classes should not be very large.

Citation

Download Citation

M. P. Quine. J. Robinson. "Efficiencies of Chi-Square and Likelihood Ratio Goodness-of-Fit Tests." Ann. Statist. 13 (2) 727 - 742, June, 1985. https://doi.org/10.1214/aos/1176349550

Information

Published: June, 1985
First available in Project Euclid: 12 April 2007

zbMATH: 0576.62061
MathSciNet: MR790568
Digital Object Identifier: 10.1214/aos/1176349550

Subjects:
Primary: 62G20
Secondary: 60F05 , 60F10

Keywords: Bahadur efficiency , central limit theorem , chi-square , Goodness-of-fit , large deviations , likelihood ratio , Pitman efficiency

Rights: Copyright © 1985 Institute of Mathematical Statistics

Vol.13 • No. 2 • June, 1985
Back to Top