Composite Likelihood Inference by Nonparametric Saddlepoint Tests
AbstractThe 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.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by DEAMS - Dipartimento di Scienze Economiche, Aziendali, Matematiche e Statistiche "Bruno de Finetti" in its series Working Papers DEAMS with number 12.
Date of creation: Jun 2013
Date of revision:
Empirical likelihood methods; Godambe information; Likelihood ratio adjustment; Nonparametric inference; Pairwise likelihood; Relative error; Robust tests; Saddlepoint test; Small sample inference;
This paper has been announced in the following NEP Reports:
You can help add them by filling out this form.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Gianni Perini).
If references are entirely missing, you can add them using this form.