The Concept of External Validity

A s it is usually phrased, the question of external validity has to do with whether the results of a behavioral study would hold for other persons, settings, times, or places. Consistent with the original notions of Campbell and Stanley (1966) and Cook and Campbell (1977), we have argued that this concept of external validity is rela-tively less important than other forms of validity when the objective of research is to test theory (Calder, Phillips, and Tybout 1981, 1982). Our position is that external validity is a matter of the applicability of behavioral research. It arises primarily through severe and rigorous tests of theory rather than by attempts to incorporate real world variables into individual studies designed to test theory. Such vari-ables only become important in the context of evaluating interventions based on theory. Lynch (1982, 1983) disputes our view of the importance