The Mantel-Haenszel procedure. 50 years of the statistical method for confounders control

The Mantel Haenszel procedure represents a simple and useful tool to obtain estimates of association, adjusted for the effect of one or more confounders. Nathan Mantel (1919-2002) was a biostatistician. In 1947 he was hired as a member of a new biometry group at the National Cancer Institute (NCI) in the National Institute of Health (NIH), Maryland, and in this time he collaborated with William M Haenszel (1910-1998). Haenszel, who was a sociologist, mathematician and statistician, had been working on interpreting the case-control studies of the connection between smoking and lung cancer, requested Mantel’s assistance on how to analyze the retrospective data. In the 1959 they published the “Statistical aspects of the analysis of data from retrospective studies of disease” on the Journal of the National Cancer Institute [1].