한국통계학회:학술대회논문집 (Proceedings of the Korean Statistical Society Conference)
- 한국통계학회 2000년도 추계학술발표회 논문집
- /
- Pages.147-152
- /
- 2000
A Bayesian Criterion for a Multiple test of Two Multivariate Normal Populations
- Kim Hea-Jung (Department of Statistics, Dongguk University) ;
- Son Young Sook (Department of Statistics , Chonnam National University)
- 발행 : 2000.11.01
초록
A Bayesian criterion is proposed for a multiple test of two independent multivariate normal populations. For a Bayesian test the fractional Bayes facto.(FBF) of O'Hagan(1995) is used under the assumption of Jeffreys priors, noninformative improper proirs. In this test the FBF without the need of sampling minimal training samples is much simpler to use than the intrinsic Bayes facotr(IBF) of Berger and Pericchi(1996). Finally, a simulation study is performed to show the behaviors of the FBF.
키워드