Cover Image

Posterior probability and conditional coverage

It is shown that under mild regularity conditions posterior probabilities are weighted averages of conditional probabilities of coverage. This is illustrated with examples from the binomial model with prior [theta]-1(1-[theta])-1 d[theta]. The converse result that conditional coverage probabilities are weighted averages of posterior probabilities is also given.
Year of publication:
1992
Authors: Swartz, T. ; Villegas, C.
Published in:
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 14.1992, 3, p. 169-173
Publisher: Elsevier
Keywords: Posterior probability conditional coverage conditional inference Bayesian inference
Type of publication: Article
Source:
Persistent link: https://www.econbiz.de/10005223431
Similar items by person