Please use this identifier to cite or link to this item:
Title: Composite Likelihood Inference by Nonparametric Saddlepoint Tests
Authors: Lunardon, Nicola
Ronchetti, Elvezio
Keywords: Empirical likelihood methodsGodambe informationLikelihood ratio adjustmentNonparametric inferencePairwise likelihoodRelative errorRobust testsSaddlepoint testSmall sample inference
Issue Date: 24-Jun-2013
Series/Report no.: DEAMS Research Paper Series 
DEAMS Research Paper Series 2013, 3
The class of composite likelihood functions provides a flexible and powerful toolkit to carry out approximate inference for complex statistical models when the full likelihood is either impossible to specify or unfeasible to compute. However, the strength of the composite likelihood approach is dimmed when considering hypothesis testing about a multidimensional parameter because the finite sample behavior of likelihood ratio, Wald, and score-type test statistics is tied to the Godambe information matrix. Consequently inaccurate estimates of the Godambe information translate in inaccurate p-values. In this paper it is shown how accurate inference can be obtained by using a fully nonparametric saddlepoint test statistic derived from the composite score functions. The proposed statistic is asymptotically chi-square distributed up to a relative error of second order and does not depend on the Godambe information. The validity of the method is demonstrated through simulation studies.
Nicola Lunardon, Elvezio Ronchetti, "Composite Likelihood Inference by Nonparametric Saddlepoint Tests", DEAMS Research Paper Series 3, 2013
Type: Book
eISBN: 978-88-8303-510-4
Appears in Collections:DEAMS Research Paper Series 2013, 3

Files in This Item:
Show full item record

CORE Recommender

Page view(s) 5

checked on Mar 29, 2023

Download(s) 20

checked on Mar 29, 2023

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.