Unconditional Versions of Several Tests Commonly Used in the Analysis of Contingency Tables

Authors: Freidlin B.¹; Gastwirth J.L.²

Source: Biometrics, Volume 55, Number 1, March 1999 , pp. 264-267(4)

Buy & download fulltext article:

Price: $48.00 plus tax (Refund Policy)

Abstract:

Summary.

By focusing on a confidence interval for a nuisance parameter, Berger and Boos (1994, Journal of the American Statistical Association89, 1012–1016) proposed new unconditional tests. In particular, they showed that, for a 2 × 2 table, this procedure generally was more powerful than Fisher's exact test. This paper utilizes and extends their approach to obtain unconditional tests for combining several 2×2 tables and testing for trend and homogeneity in a 2 ×K table. The unconditional procedures are compared to the conditional ones by reanalyzing some published biomedical data.

Keywords: Cochran-Armitage test; Cochran-Mantel-Haenszel test; Contingency tables; Exact inference; p-value; Unconditional test

Document Type: Research article

DOI: http://dx.doi.org/10.1111/j.0006-341X.1999.00264.x

Affiliations: 1: Biometric Research Branch, National Cancer Institute, 6130 Executive Blvd. EPN Rm. 739, Bethesda, Maryland 20892–7434, U.S.A. Gov, Email: reidlinb@ctep.nci.nhi. 2: Department of Statistics, George Washington University, Washington, D.C. 20052, U.S.A.

Publication date: 1999-03-01