An initial screening experiment may lead to ambiguous conclusions regarding the factors which are active in explaining the variation of an outcome variable: thus adding follow-up runs becomes necessary. We propose an objective Bayesian approach to follow-up designs, using prior distributions suitably tailored to model selection. We adopt a model discrimination criterion based on a weighted average of Kullback-Leibler divergences between predictive distributions for all possible pairs of models. When applied to real data, our method, which is fully automatic, produces results which compare favorably to previous analyses based on subjective priors. Supplementary materials are available online.

Consonni, G., Deldossi, L., Objective Bayesian model discrimination in follow-up experimental designs, <<TEST>>, 2016; 25 (3): 397-412. [doi:10.1007/s11749-015-0461-3] [http://hdl.handle.net/10807/91884]

Objective Bayesian model discrimination in follow-up experimental designs

Consonni, Guido;Deldossi, Laura
2016

Abstract

An initial screening experiment may lead to ambiguous conclusions regarding the factors which are active in explaining the variation of an outcome variable: thus adding follow-up runs becomes necessary. We propose an objective Bayesian approach to follow-up designs, using prior distributions suitably tailored to model selection. We adopt a model discrimination criterion based on a weighted average of Kullback-Leibler divergences between predictive distributions for all possible pairs of models. When applied to real data, our method, which is fully automatic, produces results which compare favorably to previous analyses based on subjective priors. Supplementary materials are available online.
Inglese
Consonni, G., Deldossi, L., Objective Bayesian model discrimination in follow-up experimental designs, <<TEST>>, 2016; 25 (3): 397-412. [doi:10.1007/s11749-015-0461-3] [http://hdl.handle.net/10807/91884]
File in questo prodotto:
File Dimensione Formato  
fulltext_Test_2016_Objective Bayesian Design.pdf

non disponibili

Tipologia file ?: Versione Editoriale (PDF)
Licenza: Non specificato
Dimensione 557.42 kB
Formato Unknown
557.42 kB Unknown   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/10807/91884
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 5
social impact