Abstract
This paper proposes a new statistical technique for deciding which of two theories is better supported by a given set of data while allowing for the possibility of drawing no conclusion at all. Procedurally similar to the classical hypothesis test, the proposed technique features three, as opposed to two, mutually exclusive data classifications: reject the null, reject the alternative, and no decision. Referred to as No-decision classification (NDC), this technique requires users to supply a simple null and a simple alternative hypothesis based on judgments concerning the smallest difference that can be regarded as an economically substantive departure from the null. In contrast to the classical hypothesis test, NDC allows users to control both Type I and Type II errors by specifying desired probabilities for each. Thus, NDC integrates judgments about the economic significance of estimated magnitudes and the shape of the loss function into a familiar procedural form.