Fuzzy and Randomized Confidence Intervals and P-Values
Open Access
- 1 November 2005
- journal article
- Published by Institute of Mathematical Statistics in Statistical Science
- Vol. 20 (4) , 358-366
- https://doi.org/10.1214/088342305000000340
Abstract
The optimal hypothesis tests for the binomial distribution and some other discrete distributions are uniformly most powerful (UMP) one-tailed and UMP unbiased (UMPU) two-tailed randomized tests. Conventional confidence intervals are not dual to randomized tests and perform badly on discrete data at small and moderate sample sizes. We introduce a new confidence interval notion, called fuzzy confidence intervals, that is dual to and inherits the exactness and optimality of UMP and UMPU tests. We also introduce a new P-value notion, called fuzzy P-values or abstract randomized P-values, that also inherits the same exactness and optimality.Keywords
This publication has 4 references indexed in Scilit:
- Interval Estimation for a Binomial ProportionStatistical Science, 2001
- Approximate Is Better than "Exact" for Interval Estimation of Binomial ProportionsThe American Statistician, 1998
- Testing Statistical HypothesesPublished by Springer Nature ,1986
- Table of Neyman-Shortest Unbiased Confidence Intervals for the Binomial ParameterBiometrika, 1960