From Testing To Decision Making: Changing How We Teach Statistics To Health Care Professionals

In their first and often only statistics course, health-care professionals are taught Bayes' theorem in the context of diagnostic testing. They learn the concepts of sensitivity/specificity and predictive value positive/negative and how Bayes' theorem can assist in diagnostic decision-making. Then the class moves on often spending weeks on tests of significance. This paper will argue for changing this practice, and instead focusing such courses on statistics for decision-making beyond diagnostic testing. It will argue that such changes will make our health-care professionals better consumers of statistical information and better decision makers.