In response to the many issues raised by Altman and Eisenbeis (A&E) [2], we will use their three-part outline. Before turning to their comments, however, we would like to take this opportunity to correct a typo in footnote 10 from our original paper [4]. The denominator of the formula is incorrect as shown, and should be .

In recent years the application of discriminant analysis to two-category (dichotomous) classification problems in empirical financial research has substantially increased. However, these studies have given relatively little attention to design and interpretation difficulties associated with discriminant analysis. Consequently, the conclusions and generalizations that can be drawn from such studies are frequently tenuous and questionable. This paper's purpose is to discuss the methodology of discriminant analysis. While the paper is oriented toward financial applications of discriminant analysis, our discussion is not peculiar to finance. Furthermore, many of the methodological issues we address are relevant to the general problem of developing and testing dichotomous classification models and arise whether model developing is by discriminant analysis or some other method.

The article focuses on the comparison of the responses in the barter case to those in the cash exchange and that no exchange cases revealed significantly more variation in the barter case. This could be interpreted as evidence that the conventional theory is incomplete. The discriminant analyses provided more direct evidence. First, in the book value versus market value analysis the author was unable to predict group membership from the situational variables. It appears that a minority, 23 percent of practitioners hold that the purchase rule, Book Value group should be applied to barters without regard to the situation. A majority 77 percent hold that either a sale or majority rule, Market Value group should be applied to barters. This division may be interpreted as the existence of two different conventional theories. Second, although one was able to identify a liquidity, acquisition and conservatism effect, the majority of the total variance remained unexplained. This may be interpreted as indicating that other implicit criteria exist which has not been identified.