Laboratory Tests of Formal Theory and Behavioral Inference

“One searches in vain for a detailed discussion of exactly how and when a model should be applied...If theorists blithely continue to prove more theorems, and applied scientists doggedly continue to gather more data, at some point data and theory might just miraculously conjoin. But we regard such a union as more likely to result from a determined effort than from a fortuitous accident.” (Fiorina and Plott 1978, 576)