© 1982 by Biometrika Trust
Robust properties of likelihood ratio tests
Department of Statistics, University of Leeds
The usual asymptotic chi-squared distribution for the likelihood ratio test statistic is based on the assumptions that the data come from the parametric model under consideration and that the parameter satisfies the null hypothesis. In this paper we examine the distribution of the likelihood ratio statistic when the data do not come from the parametric model, but when the nearest member of the parametric family still satisfies the null hypothesis. In general, the likelihood ratio statistic no longer follows an asymptotic chi-squared distribution, and an alternative statistic based on the union-intersection approach is proposed.
Key Words: Information Likelihood ratio test Robustness Union-intersection test
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
R. E. Chandler and S. Bate Inference for clustered data using the independence loglikelihood Biometrika, March 1, 2007; 94(1): 167 - 183. [Abstract] [Full Text] [PDF] |
||||
![]() |
A. M. Bertelli Governing the Quango: An Auditing and Cheating Model of Quasi-Governmental Authorities J. Public Adm. Res. Theory., April 1, 2006; 16(2): 239 - 261. [Abstract] [Full Text] [PDF] |
||||
![]() |
E. Krishnan, V. B. Lingala, and G. Singh Declines in Mortality From Acute Myocardial Infarction in Successive Incidence and Birth Cohorts of Patients With Rheumatoid Arthritis Circulation, September 28, 2004; 110(13): 1774 - 1779. [Abstract] [Full Text] [PDF] |
||||
![]() |
A. B. Whitford Decentralization and Political Control of the Bureaucracy Journal of Theoretical Politics, April 1, 2002; 14(2): 167 - 193. [Abstract] [PDF] |
||||



