Bayes factors based on test statistics

By Valen E. Johnson. 2005

122 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/ad611e2ef09f1704fcef6e8468ee487b44dabac1

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

On p-Values and Bayes Factors (2018, methodology): “Local g-Priors We now outline the derivation of a minimum test-based Bayes factor based on the F -statistic and local g-priors, as given in Johnson (2005).”
Properties of Bayes Factors Based on Test Statistics (2008, methodology): “Along somewhat different lines, I proposed a method for defining Bayes factors by modelling test statistics (Johnson, 2005; hereafter J05).”
Mixtures of g-Priors in Generalized Linear Models (2015, methodology): “In Section 2, we begin by reviewing g-priors in GLMs and corresponding (approximate) Bayes factors, and the closely related Bayes factors based on test statistics (Johnson 2005, 2008; Hu and Johnson 2009; Held, Sabanés Bové, and Gravestock 2015).”
Bayesian Model Assessment Using Pivotal Quantities (2007, unknown): “…to avoid PPP simulation are currently under investigation and include approaches based on modeling the marginal distribution of pivotal quantities as mixtures of low-dimensional parametric densities and computing “average” Bayes factors from the pivotal quantities themselves (e.g., Johnson (2005)).”
Simple relation between Bayesian order-restricted and point-null hypothesis tests (2014, methodology): “…allows immediate one-sided extensions for model comparison methods such as BIC (Raftery, 1995; Schwarz, 1978), fractional Bayes factors (O’Hagan, 1995), intrinsic Bayes factors (Berger and Pericchi, 1996; Berger and Mortera, 1999), and Bayes factors calculated from test statistics (Johnson, 2005).”
How the Maximal Evidence of P-Values Against Point Null Hypotheses Depends on Sample Size (2016, background): “The above minimum Bayes factors (3) and (4) are based on a test statistic (z) (or a p-value p) and they are special cases of so-called (minimum) test-based Bayes factors (TBFs) (Johnson 2005, 2008).”
Bayesian Inference for Kendall’s Rank Correlation Coefficient (2018, methodology): “2 Modeling Test Statistics In order to compute Bayes factors for Kendall’s τ we start with the approach pioneered by Johnson (2005) and Yuan and Johnson (2008).”