Posterior Predictive $p$-Values
Meng, Xiao-Li
Ann. Statist., Tome 22 (1994) no. 1, p. 1142-1160 / Harvested from Project Euclid
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 $2\alpha$.
Publié le : 1994-09-14
Classification:  Bayesian $p$-value,  Behrens-Fisher problem,  discrepancy,  multiple imputation,  nuisance parameter,  pivot,  $p$-value,  significance level,  tail-area probability,  test variable,  Type I error,  62F03,  62A99
@article{1176325622,
     author = {Meng, Xiao-Li},
     title = {Posterior Predictive $p$-Values},
     journal = {Ann. Statist.},
     volume = {22},
     number = {1},
     year = {1994},
     pages = { 1142-1160},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176325622}
}
Meng, Xiao-Li. Posterior Predictive $p$-Values. Ann. Statist., Tome 22 (1994) no. 1, pp.  1142-1160. http://gdmltest.u-ga.fr/item/1176325622/