Modeling default prediction with earnings management

Abstract

This study explores whether taking into account real earnings management improves specification of the default prediction model based on the Z-score methodology for Chinese listed companies. We demonstrate that the model proposed by Altman (1968) overestimates (underestimates) the Z-score and thus the survival probability for firms engaging in aggressive (minor or no) income-increasing manipulation. By contrast, our inclusion of the indicator variable for real earnings management considerably enhances the explanatory power of Z-score factors for firm survival/default. With respect to the ability to predict out-of-sample default, our findings suggest that the accounting-based credit scoring model adjusted for real earnings management unanimously yields a greater prediction accuracy rate and a lower false loan rejection rate than the unadjusted scoring model for financially non-distressed firms.