article
Cochran–Mantel–Haenszel test with bivariate binomial model on surrogate marker analysis
Buddhananda Banerjeea✉, Atanu Biswasb, S. H. Ongc d, Saumen Mandale
- aIndian Institute Technology Kharagpur, Kharagpur, India
- bIndian Statistical Institute, Kolkata, India
- cDepartment of Actuarial Science and Applied Statistics, UCSI University, Kuala Lumpur, Malaysia
- dInstitute of Mathematical Sciences, University of Malaya, Kuala Lumpur, Malaysia
- eUniversity of Manitoba, Winnipeg, MB, Canada
- ✉Corresponding author
Communications in Statistics Case Studies Data Analysis and ApplicationsTaylor & Francis2018-10-02 0 citations21 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
The standard Cochran–Mantel–Haenszel (CMH) test is useful for testing common odds ratio for multiple 2 × 2 contingency tables under the assumption of hypergeometric/product-binomial model. In this article, we shed light on the modification of the CMH test in a bivariate binomial setup with the presence of surrogate markers. We illustrate that the surrogate information can be successfully incorporated to improve the performance of the CMH test procedure by using a bivariate binomial model.