Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/8229
Title: | One-sided tests in shared frailty models | Authors: | CLAESKENS, Gerda NGUTI, Rosemary JANSSEN, Paul |
Issue Date: | 2008 | Publisher: | SPRINGER | Source: | TEST, 17(1). p. 69-82 | Abstract: | Tests for the presence of heterogeneity in frailty models use an alternative hypothesis in which the heterogeneity parameter is subject to an inequality constraint. As a result, the classical likelihood ratio asymptotic chi-square distribution theory is no longer valid. Our main result states the limiting distribution of the likelihood ratio and score statistic for the one-sided testing problem. The resulting distribution is a mixture of chi-square distributed random variables. The results are shown for gamma and positive stable frailty distributions, and hold when covariate information is present. A data example illustrates the tests. We also assess, in a simulation study, the performance of the tests regarding the significance level and power. | Notes: | Katholieke Univ Leuven, ORSTAT, B-3000 Louvain, Belgium. Katholieke Univ Leuven, Univ Ctr Stat, B-3000 Louvain, Belgium. Univ Nairobi, Dept Math, Nairobi, Kenya. Univ Hasselt, Ctr Stat, Hasselt, Belgium.Claeskens, G, Katholieke Univ Leuven, ORSTAT, Naamsestr 69, B-3000 Louvain, Belgium.gerda.claeskens@econ.kuleuven.be | Keywords: | inference under inequality constraints; frailty models; likelihood ratio test; mixture of chi(2)-distributions; score test; survival data | Document URI: | http://hdl.handle.net/1942/8229 | ISSN: | 1133-0686 | e-ISSN: | 1863-8260 | DOI: | 10.1007/s11749-006-0023-9 | ISI #: | 000254462600012 | Category: | A1 | Type: | Journal Contribution | Validations: | ecoom 2009 |
Appears in Collections: | Research publications |
Show full item record
SCOPUSTM
Citations
24
checked on Sep 2, 2020
WEB OF SCIENCETM
Citations
29
checked on May 2, 2024
Page view(s)
128
checked on Jun 19, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.