The Model as a Classification Tool
Because the model distinguishes manipulators from nonmanipulators, I assessed its usefulness as a classification tool. This section discusses the probability cutoffs associated with different costs of making classification errors. The model can make two types of errors: It can classify a company as a nonmanipulator when it manipulates (a Type I error), or it can classify a company as a manipulator when it does not manipulate (a Type II error). The probability cutoffs that minimize the expected costs of misclassification depend on costs associated with