Likelihood Ratio Tests and Intersection- Union Tests
نویسنده
چکیده
The likelihood ratio test (LRT) method is a commonly used method of hypothesis test construction. The intersection-union test (JUT) method is a less commonly used method. We will explore some relationships between these two methods. We show that, under some conditions, both methods yield the same test. But, we also describe conditions under which the size-a JUT is uniformly more powerful than the size-a LRT. We illustrate these relationships by considering the problem of testing Ho : min{1J.lll, 1J.l21} = 0 versus Ha min{lJ.lll, 1J.l21} > 0, where J.ll and J.l2 are means of two normal populations.
منابع مشابه
Union-Intersection Multiple Comparison Tests
The union-intersection principle yields a class of multiple comparison tests that include the classical Scheffé tests for analysis of variance, and are easily applied to any likelihood ratio test. Examples are given.
متن کاملMore Powerful Tests for the Sign Testing Problem
For i = 1, ... ,p, let Xi!, ... ,Xini denote independent random samples from normal populations. The ith population has unknown mean Jli and unknown variance a;. We consider the sign testing problem of testing Ho : Jli :::; ai, for some i = 1, ... ,p, versus HI : Jli > ai, for all i = 1, ... ,p, where al,." ,ap are fixed constants. Here, HI might represent p different standards that a product m...
متن کاملP 3 Approach to Intersection - Union Testing of Hypotheses 1
Recent applications of Statistics often leads one to encounter testing problems where the original hypothesis of interest comprises of the union of several sub-hypothesis. In the framework of such Intersection-Union testing of hypothesis, in contrast to the usual Union-Intersection framework, a subhypothesis therein may specify a parameter or a function of some of the parameters of the underlyi...
متن کاملTesting for the Supremacy of a Multinomial Cell Probability
Tests for the supremacy of a multinomial cell probability are developed. The tested null hypothesis states that a particular cell of interest is not more probable than all others. Rejection of this null leads to the conclusion that the cell of interest has a strictly greater probability than all other cells. The null hypothesis constrains the multinomial probability vector to a non-convex regio...
متن کاملSome Improved Tests for Multivariate One-Sided Hypotheses*
Multivariate one-sided hypothesis-testing problems are very common in clinical trials with multiple endpoints. The likelihood ratio test (LRT) and union-intersection test (UIT) are widely used for testing such problems. It is argued that, for many important multivariate one-sided testing problems, the LRT and UIT fail to adapt to the presence of subregions of varying dimensionalities on the bou...
متن کامل