Bayesian index of superiority and the p-value of the conditional test for Poisson parameters

DOI10.14490/JJSS.46.99MaRDI QIDQ5281629zbMATH OpenOpenAlexFDO

Authors Masaaki Doi

Publication date 26 July 2017

Published in JOURNAL OF THE JAPAN STATISTICAL SOCIETY (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1606.01324

zbMATH Keywords

binomial distributionbeta distributionclinical trialnon-informative priorcumulative distribution functionsconditional testPoisson parametersBayesian indexconditional power prior

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Bayesian inference (62F15) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Abstract: We consider the problem of comparing two Poisson parameters from the Bayesian perspective. Kawasaki and Miyaoka (2012b) proposed the Bayesian index $P(lambd{a}_1<lambd{a}_2|X_1,X_2)$ and expressed it using the hypergeometric series. In this paper, under some conditions, we give four other expressions of the Bayesian index in terms of the cumulative distribution functions of beta, $F$, binomial, and negative binomial distribution. Next, we investigate the relationship between the Bayesian index and the $p$-value of the conditional test with the null hypothesis $H_0:lambd{a}_{1}geqlambd{a}_2$ versus an alternative hypothesis $H_1:lambd{a}_1<lambd{a}_2$. Additionally, we investigate the generalized relationship between $P(lambd{a}_1/lambd{a}_2<c|X_1,X_2)$ and the $p$-value of the conditional test with the null hypothesis $H_0:lambd{a}_1/lambd{a}_{2}geqc$ versus the alternative $H_1:lambd{a}_1/lambd{a}_2<c$. We illustrate the utility of the Bayesian index using analyses of real data. Our finding suggests that the Bayesian index can potentially be useful in an epidemiology and in a clinical trial.

Recommendations

• A Bayesian inference of \(P( \lambda_1< \lambda_2)\) for two Poisson parameters
• On the Bayesian index of superiority and the \(p\)-value of the Fisher exact test for binomial proportions
• A Bayesian non-inferiority index for two Poisson parameters
• The discrepancy of \(P\)-values and posterior probability in Poisson distribution
• A Bayesian inferiority index for mean from normal distributions

Cited in

(4)

• A Bayesian inferiority index for mean from normal distributions
• A Bayesian non-inferiority index for two Poisson parameters
• A Bayesian inference of \(P( \lambda_1< \lambda_2)\) for two Poisson parameters
• On the Bayesian index of superiority and the \(p\)-value of the Fisher exact test for binomial proportions

This page was built for publication: Bayesian index of superiority and the \(p\)-value of the conditional test for Poisson parameters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5281629)