This publication is the methodological foundation of my proposed theoretical framework for reasoning about generalizability of randomized trials. We introduce a new class of effect measures, the counterfactual outcome state transition (COST) parameters, and show how they can be used to derive results with important implications for meta-analysis and effect heterogeneity.
Recommended citation: Huitfeldt A, Goldstein A, Swanson SA. "The choice of effect measure for binary outcomes: Introducing counterfactual outcome state transition parameters". Epidemiologic Methods 2018, 2161-962X.