The Potential Misinterpretation Problem of Residual
Based Models Due to Industry Misclassification

DOI 10.14707/ajbr.170028

Chong Wang
Graduate School of Business and Public Policy, Naval Postgraduate School, USA
Lili Shao
School of Accounting, Shanghai Lixin University of Accounting and Finance, China
Chuan Zhang
School of Economics & Management, Shanghai Maritime University, China


Accounting researchers frequently employ industry-specific residual based models to draw inferences. Examples include discretionary accruals in Jones (1991) and modified Jones model (1995), and accruals quality in Francis et al. (2005). This paper illustrates that the interpretation of the residual terms is potentially subject to the problem that arises from industry misclassification. In an industry-specific cross-sectional regression, the assumed homogeneity within the same industry is problematic because the industry classification system is noisy, and thus large magnitude residuals are potentially caused by misclassified observations. Moreover, the misclassification may not happen randomly. If firms with certain characteristics are more likely to be misclassified, directional biases rather than pure noise may emerge. In firm-specific time-series settings, the implied stationarity over time for the same firm is also questionable. Firms face external shocks and/or internal changes. The big magnitude residuals could capture those “shock” or “change” years. Given that researchers often investigate whether there exists earnings management around special events, such as M&A or equity issuance, it would be necessary to distinguish between whether abnormal accruals around the event is due to earnings management or simply non-stationarity.

Keywords: Industry Models, Residuals, Accruals Quality, Illiquidity Discount, Diversification Discount


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.