Measures of Predictive Success for Rating Functions

Aim of our paper is to develop an adequate measure of predictive success and accuracy of rating functions. At first, we show that the common measures of rating accuracy, i.e. area under curve and accuracy ratio, respectively, lack of informative value of single rating classes. Selten (1991) builds up an axiomatic framework for measures of predictive success. Therefore, we introduce a measure for rating functions that fulfills the axioms proposed by Selten (1991). Furthermore, an empirical investigation analyzes predictive power and accuracy of Standard & Poor's and Moody's ratings, and compares the rankings according to area under curve and our measure.