Bootstrap Tests for Multivariate Event Studies

23 Pages Posted: 11 Feb 1999

Date Written: October 1998

Abstract

Statistical tests for multivariate event studies, exact or asymptotic, have been derived based on multivariate normality. As it has been documented that the performances of these tests are not satisfactory because stock returns are far from normally distributed, especially for daily returns, this paper proposes a bootstrap alternative to multivariate event studies that does not require a specific distributional assumption. The Monte Carlo experiments based on daily returns data show that the bootstrap tests outperform the traditional tests by having close rejection rates to the nominal significance levels. The traditional tests, in contrast, tend to reject the null hypotheses too often.

JEL Classification: C13,C53,G14

Suggested Citation

Chou, Pin-Huang, Bootstrap Tests for Multivariate Event Studies (October 1998). Available at SSRN: https://ssrn.com/abstract=144420 or http://dx.doi.org/10.2139/ssrn.144420

Pin-Huang Chou (Contact Author)

National Central University ( email )

Department of Finance
Taoyuan, 32001
Taiwan
886-3-4227151 ext 66270 (Phone)
886-3-4252961 (Fax)

HOME PAGE: http://mgt.ncu.edu.tw/~choup