A Robust Mantel-Haenszel Test using Probabilistic Approach
Mantel-Haenszel test statistic is one of the common test statistics for test of significance variation between/among factors and its application is similar to One-way Analysis of Variance and Kruskal-Wallis test statistics. The method can be categorized as non-parametric and robust in nature. It has been used over time by researchers for test of significance variation among factors. Critical look at the test statistic reveals it weakness which is inability to remove variation among factors in terms of sample size or weight. To remove biasness in the test of hypothesis with Mantel-Haenszel test as the statistic, there is need for proper and appropriate modification. This paper addressed the noticed short fall of the test statistic with illustrative example for easy computation by users. Similar data used by researchers in the past was also used in the study using the propose method called modified Mantel-Haenszel test statistic.
Mantel N. (1966). Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemother. Rep.;50:163–170.
Nathan Mantel and William Haenszel (1959). "Statistical aspects of the analysis of data from retrospective studies of disease". Journal of the National Cancer Institute 22 (4): 719–748
Nathan Mantel (1963). "Chi-Square Tests with One Degree of Freedom, Extensions of the Mantel-Haenszel Procedure". Journal of the American Statistical Association 58 (303): 690–700
Peto R, Peto J. (1972). Asymptotically efficient rank invariant test procedures (with discussion) J. Roy. Statist. Soc. A.;135:185–206
Wallenstein S, Wittes J. (1993). The power of the Mantel-Haenszel test for grouped failure time data. Biometrics;49:1077–1087.
William G. Cochran (1954). "Some Methods for Strengthening the Common χ2 Tests". Biometrics 10 (4): 417–451
Copyright (c) 2019 Awopeju K. Abidemi, Umeh Edith Uzoma, Dr., Ajibade Bright F., Dr.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided that the original work is properly cited.