Corporate Financial Fraud: An Application of Detection Controlled Estimation

Abstract:     
The paper studies corporate financial fraud and detection using an empirical framework that models the strategic interdependence between fraud and detection and accounts for the possibility that some fraud remains undetected (incomplete detection). The framework first models fraud as a discrete choice and is then extended to model the magnitude of fraud. The paper shows that failure to account for incomplete detection can lead to significant downward biases in estimating the effects of various factors on the likelihood of fraud. By modeling fraud and detection in two separate equations, the model allows one to study the impact of the regulator’s budget on fraud detection and the strategic interdependence between fraud and detection. Furthermore, the empirical model in the paper has a number of potential applications.

Number of Pages in PDF File: 77

Keywords: Fraud, detection, corporate misreporting, monitoring, detection controlled estimation, incomplete detection, partial observability, probit models, Tobit models, simultaneous equation models

JEL Classification: G34, G39, C35, M41, K22, K42

working papers series