THE CONNECTICUT CRACKDOWN ON SPEEDING.

Social research frequently encounters the task of evaluating change produced in non-randomly selected groups by events which are beyond the researcher's control. The social scientist must verify that there has in fact been a change, and that the indicated event is its cause. This article introduces, in the context of a problem in applied sociology and the sociology of law, a mode of analysis designed to deal with a common class of situations in which research must proceed without the benefit of experimental control. The general methodology expounded here is termed "quasi-experimental analysis." The specific mode of analysis is the "interrupted time-series design." Perhaps its fundamental credo is that lack of control and lack of randomization are damaging to inferences of cause and effect only to the extent that a systematic consideration of alternative explanations reveals some that are plausible. The 1955 crackdown on speeding in the state of Connecticut furnishes an apt example of the potentialities of such quasi-experimental analysis.