Detecting Long-Run Abnormal Stock Returns: The Empirical Power and Specification of Test Statistics

Posted: 9 May 1998

See all articles by Brad M. Barber

Brad M. Barber

University of California, Davis

John D. Lyon

The University of Melbourne, Department of Accounting and Business Information Systems

Date Written: January 1996

Abstract

We analyze the empirical power and specification of test- statistics in event studies designed to detect long-run (one to five-year) abnormal stock returns. We consider (1) the calculation of long-run abnormal returns by comparing summed monthly abnormal returns (cumulative abnormal returns) to holding period abnormal returns (buy-and-hold abnormal returns), (2) the construction of an appropriate return benchmark by considering the use of reference portfolios, control firms, and an application of the Fama-French three-factor model, and (3) the impact of sampling biases. When long-run abnormal returns are calculated as the buy-and-hold return of a sample firm less the buy-and-hold return of a reference portfolio (such as a market index), we document that test-statistics are significantly negatively biased. However, this negative bias is alleviated when buy-and-hold abnormal returns are calculated as returns of sample firms less returns of an appropriately selected control firm.

JEL Classification: G12, G14

Suggested Citation

Barber, Brad M. and Lyon, John D., Detecting Long-Run Abnormal Stock Returns: The Empirical Power and Specification of Test Statistics (January 1996). Available at SSRN: https://ssrn.com/abstract=7197

Brad M. Barber (Contact Author)

University of California, Davis ( email )

Graduate School of Management
One Shields Avenue
Davis, CA 95616
United States
530-752-0512 (Phone)
530-752-2924 (Fax)

John D. Lyon

The University of Melbourne, Department of Accounting and Business Information Systems ( email )

Victoria
Melbourne, 3010
Australia

HOME PAGE: http://www.abis.unimelb.edu.au/who/staff/john_lyon.html

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
6,467
PlumX Metrics