Extending conventional priors for testing general hypotheses in linear models

By Maria J. Bayarri, G. Garc'ia-Donato. 2007

83 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/1ec49210a17e51d43a60217f8ba9ce20ba7b2137

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Bayesian Analysis of Factorial Designs (2017, background): “Not surprisingly, this hierarchical specification is popular among Bayesian analysts; examples with linear models include Bayarri and Garcia-Donato (2007), Gelman (2005), Liang, Paulo, Molina, Clyde, and Berger (2008), and Zellner and Siow (1980). When gd is treated as a parameter, a prior is needed”
Default Bayes factors for ANOVA designs (2012, methodology): “We use prior odds to add context to our Bayes factor analysis of Bem’s (2011) claim of extrasensory perception of future events that cannot otherwise be known (Rouder & Morey, 2011).”
Harold Jeffreys’s Theory of Probability Revisited (2008, background): “See Bayarri and Garcia-Donato ( 2007) for a modern extension of this perspective to general testing problems.”
Testing hypotheses via a mixture estimation model (2014, background): “…is wide open to controversy and divergent opinions (Jeffreys, 1939; Bernardo, 1980; Berger, 1985; Aitkin, 1991; Berger and Jefferys, 1992; De Santis and Spezzaferri, 1997; Bayarri and Garcia-Donato, 2007; Christensen et al., 2011; Johnson and Rossell, 2010; Gelman et al., 2013a; Robert, 2014).”
The Effective Sample Size (2014, methodology): “Other model selection priors which make similar use of n can be found in Bayarri and García-Donato (2007, 2008), Bayarri et al. (2009), George (2000), Liang et al. (2008), Verdinelli and Wasserman (1995), and Zellner (1986).”
A Default Bayesian Hypothesis Test for ANOVA Designs (2012, methodology): “Here we showed how the regression framework can be seamlessly carried over to ANOVA designs, at the same time illustrating various default prior distributions, such as Zellner’s g-prior, the JZS approach, and the hyper-g approach (for a similar approach see Bayarri and Garcı́a-Donato 2007).”
Compatibility of prior specifications across linear models (2008, methodology): “The Hald data have been also analyzed in a Bayesian objective framework, in particular by Berger and Pericchi (1996b) using intrinsic Bayes factor, and by Casella and Moreno (2006) and Moreno and Giron (2007) using intrinsic priors.”