Intersection-Union Tests: Theory and Examples - Department of Statistics - Purdue University Skip to main content

Myra Samuels Memorial Lecture

Intersection-Union Tests: Theory and Examples

Roger L. Berger
School of Mathematical and Natural Sciences, Arizona State University

Start Date and Time: Fri, 29 Apr 2016, 10:30 AM

End Date and Time: Fri, 29 Apr 2016, 11:30 AM

Venue: WTHR 320

Refreshments: HAAS 111 at 9:45 AM

Abstract:

The intersection-union method of hypothesis test construction is a simple and useful method, if the null hypothesis is conveniently expressed as a union of sets. In this lecture, we define intersection-union tests (IUT’s) and discuss their basic properties. We discuss relationships between IUT’s and other common tests such as likelihood ratio tests (LRT’s), and we discuss situations in which IUT’s are uniformly more powerful than LRT’s. Numerous examples or IUT’s will be presented, including bioequivalence tests, determination of the minimum effective dose or the maximum tolerated dose of a drug, and determination of the time span during which a drug’s blood concentration exceeds a certain threshold.

Purdue Department of Statistics, 150 N. University St, West Lafayette, IN 47907

Phone: (765) 494-6030, Fax: (765) 494-0558

© 2023 Purdue University | An equal access/equal opportunity university | Copyright Complaints

Trouble with this page? Disability-related accessibility issue? Please contact the College of Science.