Posterior Predictive $p$-Values
Xiao‐Li Meng · The Annals of Statistics · 1994
Extending work of Rubin, this paper explores a Bayesian counterpart of the classical $p$-value, namely, a tail-area probability of a "test statistic" under a null hypothesis. The Bayesian formulation, using posterior predictive replications of the data, allows a "test statistic" to depend on both data and unknown (nuisance) parameters and thus permits a direct measure of the discrepancy between sample and population quantities. The tail-area probability for a "test statistic" is then found under the joint posterior distribution of replicate data and the (nuisance) parameters, both conditional on the null hypothesis. This posterior predictive $p$-value can also be viewed as the posterior mean of a classical $p$-value, averaging over the posterior distribution of (nuisance) parameters under the null hypothesis, and thus it provides one general method for dealing with nuisance parameters. Two classical examples, including the Behrens-Fisher problem, are used to illustrate the posterior predictive $p$-value and some of its interesting properties, which also reveal a new (Bayesian) interpretation for some classical $p$-values. An application to multiple-imputation inference is also presented. A frequency evaluation shows that, in general, if the replication is defined by new (nuisance) parameters and new data, then the Type I frequentist error of an $\alpha$-level posterior predictive test is often close to but less than $\alpha$ and will never exceed $2\alpha$.
Cited by 785 works. doi:10.1214/aos/1176325622 Open-access PDF
Authors
References
- Stochastic processes
- Multiple Imputation for Nonresponse in Surveys
- Continuous Univariate Distributions.
- Bayesianly Justifiable and Relevant Frequency Calculations for the Applied Statistician
- Sampling and Bayes' Inference in Scientific Modelling and Robustness
- Performing Likelihood Ratio Tests with Multiply-Imputed Data Sets
- Large-Sample Significance Levels from Multiply Imputed Data Using Moment-Based Statistics and anFReference Distribution
- Significance levels from repeated p-values with multiply imputed data
- Generalized p-Values in Significance Testing of Hypotheses in the Presence of Nuisance Parameters
- An optimal property of the likelihood ratio statistic