Useful model checking tools can be constructed by measuring the distance between a prior distribution that concentrates most of its mass around a model of interest, and the resulting posterior distribution. In this paper we use this approach to construct a diagnostic measure for detecting lack of fit in discrete data, with special focus on binomial data. We begin by constructing a suitable probability model “around” the model of interest, via a Dirichlet Process elaboration. We derive the resulting diagnostic and show that, approximately, it is the sum of two terms: the first is the logarithm of the Bayes factor and the second is proportional to the Pearson chi-square statistics. We give details of a simulation algorithm for computing the diagnostic and illustrate its use in an application to biomedical data.

A Dirichlet process elaboration diagnostic for binomial goodness of fit / C. Carota; G. Parmigiani. - In: TEST. - ISSN 1133-0686. - 7(1998), pp. 133-145.

A Dirichlet process elaboration diagnostic for binomial goodness of fit

CAROTA, Cinzia;
1998

Abstract

Useful model checking tools can be constructed by measuring the distance between a prior distribution that concentrates most of its mass around a model of interest, and the resulting posterior distribution. In this paper we use this approach to construct a diagnostic measure for detecting lack of fit in discrete data, with special focus on binomial data. We begin by constructing a suitable probability model “around” the model of interest, via a Dirichlet Process elaboration. We derive the resulting diagnostic and show that, approximately, it is the sum of two terms: the first is the logarithm of the Bayes factor and the second is proportional to the Pearson chi-square statistics. We give details of a simulation algorithm for computing the diagnostic and illustrate its use in an application to biomedical data.
7
133
145
http://www.springerlink.com
Bayesian model criticism; Binomial data; Logarithmic divergence; Chi-square statistics
C. Carota; G. Parmigiani
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2318/60009
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact