A design-based approximation to the BIC in finite population sampling

Fabrizi, Enrico; Lahiri, Partha

In this article, various issues related to the implementation of the usual Bayesian Information Criterion (BIC) are critically examined in the context of modelling for finite populations. A suitable design-based approximation to the BIC is proposed in order to avoid the derivation of the exact likelihood of the sample which is often very complex in a finite population sampling. The approximation is justified using a theoretical argument and a Monte Carlo simulation study.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10446/330

Titolo:	A design-based approximation to the BIC in finite population sampling
Tutti gli autori:	FABRIZI, ENRICO; LAHIRI, PARTHA
Data di pubblicazione:	2007
Tipologia specifica:	working paper
Abstract (eng):	In this article, various issues related to the implementation of the usual Bayesian Information Criterion (BIC) are critically examined in the context of modelling for finite populations. A suitable design-based approximation to the BIC is proposed in order to avoid the derivation of the exact likelihood of the sample which is often very complex in a finite population sampling. The approximation is justified using a theoretical argument and a Monte Carlo simulation study.
Nelle collezioni:	Working papers at the Lorenzo Mascheroni Dep. of Mathematics, Statistics, Computing and Applications - Quaderni del Dip. di Matematica, statistica, informatica e applicazioni Lorenzo Mascheroni

File allegato/i alla scheda:

File	Descrizione	Dimensione del file	Formato	Tipologia	Licenza
WPMateRi04(2007)FabriziLahiri.pdf		450.52 kB	Adobe PDF	N/A		Open Access Visualizza/Apri

Citazioni
ND