Approximations and consistency of Bayes factors as model dimension grows

109 citations recorded by the source corpus.

How researchers see this paper

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

MODEL SELECTION FOR HIGH-DIMENSIONAL, MULTI-SEQUENCE CHANGE-POINT PROBLEMS (2012, methodology): “Mixtures of g-priors have been used for high-dimensional Gaussian models in Berger, Ghosh, and Mukhopadhyay (2003) and were shown to have desirable properties in Liang et al. (2008).”
Model Selection in the Presence of Incidental Parameters (2015, unknown): “Examples are Berger et al. (2003) and Chakrabarti and Ghosh (2006), who analyze the use of the Laplace approximation in large-dimensional exponential families to compute the Bayes factor and achieve a consistent selector.”
Testing hypotheses via a mixture estimation model (2014, background): “This occurs despite the existence of an overall consistency proof for the Bayes factor (Berger et al., 2003; Rousseau, 2007; McVinish et al., 2009).”
The Effective Sample Size (2014, background): “Sample size is well-defined if one has i.i.d real observations, but is not well-defined for vector observations or in non-i.i.d. settings, as has been noted in Kass and Wasserman (1995), Pauler (1998), Weakliem (1999), and Berger et al. (2003), among others.”
Estimating the Integrated Likelihood via Posterior Simulation Using the Harmonic Mean Identity (2006, methodology): “The definition (17) of BIC, on which BICM as defined by (18) is based, is adequate for fixed effects models, but not for hierarchical or random effects models, as shown for example by Pauler (1998) and Berger, Ghosh, and Mukhopadhyay (2003).”