Statistical Analysis of the Additive and Multiplicative Hypotheses of Multiple Exposure Synergy for Cohort and Case-Control Studies

Abstract

This paper considers hypotheses tests for synergistic relationships in epidemiological studies. Two hypotheses are considered. First, I develop tests of the additive hypothesis which states that the combined risk from two sources of exposure is the sum of each risk taken separately. I then develop tests for the hypothesis that a multiplicative relationship exists for the risks, i.e., that the combined risk is consistent with the multiplication of the individual risks. Following standard practice in epidemiological studies I consider tests for both case-referent and cohort (standardized mortality rate) type studies.