52 Pages Posted: 16 Jun 2017
Date Written: May 31, 2017
Outliers represent a fundamental challenge in empirical finance research. We investigate whether the routine techniques used in finance research to identify and treat outliers are appropriate for the data structures we observe in practice. We then propose a multivariate outlier identification strategy and show this method effectively identifies outliers, tests for their influence, and minimizes the bias they cause in both cross-sectional and panel regressions. We empirically test this method using replications of four recently published studies in premier finance journals to show how adjusting for multivariate outliers can lead to significantly different results.
Keywords: Research Design, Financial Data, Winzorize, Outliers
JEL Classification: G00, G10, G20, G30
Suggested Citation: Suggested Citation
Adams, John C. and Hayunga, Darren K. and Mansi, Sattar and Reeb, David M., Identifying Outliers in Finance (May 31, 2017). Available at SSRN: https://ssrn.com/abstract=2986928