Empirical Bayes factors for common hypothesis tests

Bayes factors for composite hypotheses have difficulty in encoding vague prior knowledge, leading to conflicts between objectivity and sensitivity including the Jeffreys-Lindley paradox. To address these issues we revisit the posterior Bayes factor, in which the posterior distribution from the data at hand is re-used in the Bayes factor for the same data. We argue that this is biased when calibrated against proper Bayes factors, but propose bias adjustments to allow interpretation on the same scale. In the important case of a regular normal model, the bias in log scale is half the number of parameters. The resulting empirical Bayes factor is closely related to the widely applicable information criterion. We develop test-based empirical Bayes factors for several standard tests and propose an extension to multiple testing closely related to the optimal discovery procedure. When only a P-value is available, such as in non-parametric tests, we obtain a Bayes factor calibration of 10p. We propose interpreting the strength of Bayes factors on a logarithmic scale with base 3.73, reflecting the sharpest distinction between weaker and stronger belief. Empirical Bayes factors are a frequentist-Bayesian compromise expressing an evidential view of hypothesis testing.