The Bayesian model consists of the prior–likelihood pair. A prior–data conflict arises whenever the prior allocates most of its mass to regions of the parameter space where the likelihood is relatively low. Once a prior–data conflict is diagnosed, what to do next is a hard question to answer. We propose an automatic prior elicitation that involves a two-component mixture of a diffuse and an informative prior distribution that favours the first component if a conflict emerges. Using various examples, we show that these mixture priors can be useful in regression models as a device for regularizing the estimates and retrieving useful inferential conclusions.

Avoiding prior–data conflict in regression models via mixture priors

Egidi L.
;
Pauli F.;Torelli N.
2022-01-01

Abstract

The Bayesian model consists of the prior–likelihood pair. A prior–data conflict arises whenever the prior allocates most of its mass to regions of the parameter space where the likelihood is relatively low. Once a prior–data conflict is diagnosed, what to do next is a hard question to answer. We propose an automatic prior elicitation that involves a two-component mixture of a diffuse and an informative prior distribution that favours the first component if a conflict emerges. Using various examples, we show that these mixture priors can be useful in regression models as a device for regularizing the estimates and retrieving useful inferential conclusions.
29-lug-2021
Pubblicato
https://onlinelibrary.wiley.com/doi/10.1002/cjs.11637
File in questo prodotto:
File Dimensione Formato  
Egidi_Avoiding prior data conflict in regression models via mixture priors.pdf

accesso aperto

Descrizione: articolo
Tipologia: Documento in Versione Editoriale
Licenza: Creative commons
Dimensione 928.3 kB
Formato Adobe PDF
928.3 kB Adobe PDF Visualizza/Apri

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: https://hdl.handle.net/11368/2993048
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 4
social impact