Why a Trade-Off? The Relationship between the External and Internal Validity of Experiments

Abstract

Much of the methodological discussion around experiments in economics and other social sciences is framed in terms of the notions of internal and external validity. The standard view is that internal validity and external validity stand in a relationship best described as a trade-off. However, it is also commonly held that internal validity is a prerequisite to external validity. This article addresses the problem of the compatibility of these two ideas and analyzes critically the standard arguments about the conditions under which a trade-off between internal and external validity arises. Our argument stands against common associations of internal validity and external validity with the distinction between field and laboratory experiments and assesses critically the arguments that link the artificiality of experimental settings done in the laboratory with the purported trade-off between internal and external validity. We conclude that the idea of a trade-off or tension between internal and external validity seems, upon analysis, far less cogent than its intuitive attractiveness may lead us to think at first sight.