Review of Quantitative Finance and Accounting, 14 (2000): 361±380
# 2000 Kluwer Academic Publishers. Manufactured in The Netherlands.
A Complete Nonparametric Event Study Approach
601 South Morgan Street (M/C 168), University of Illinois at Chicago, Chicago, IL 60607
Texas Christian University, Box 32868, Fort Worth, TX 76129
368 Fair®eld Road, U-41RE, University of Connecticut, Storrs, CT 06269
Abstract. Event studies have been used to examine the direction, magnitude, and speed of security price
reactions to various phenomenon. Concerns over the lack of normality in stock return distributions motivated the
introduction of nonparametric test statistics in the event study literature. A parametric procedure (OLS), however,
has been extensively employed in the estimation of parameters for the market model. This paper, in contrast,
applies Theil's nonparametric regression in the estimation of abnormal returns; an approach which is distribution
free and provides a complete nonparametric approach for the detection of abnormal performance.
Simulation results indicate Theil's estimation procedure offers a slight improvement in power in the detection
of abnormal performance over the traditionally employed methodology. The results suggest employing Theil's
nonparametric estimation procedure combined with the rank statistic. This complete nonparametric combination
offers similar power with fewer underlying assumptions.
Key words: nonparametric, event study, methodology
Researchers in various ®elds are interested in how new information affects stock prices.
Since the seminal article of Fama et al. (1969), event studies have been frequently
employed to investigate if new information imparts a change in equity value. Applications
of event studies are numerous and include governmental actions, capital budgeting
decisions, acquisitions and mergers, and changes in management.
Crucial to all event studies is the ability to accurately detect abnormal performance. In
two widely cited papers in ®nance, Brown and Warner (1980; 1985) examine the ability
of various event study methodologies to appropriately detect abnormal performance.
Using stock returns from the NYSE and AMEX, the authors ®nd that event studies based
on the ordinary least squares (OLS) estimation of the market model which use
parametric tests are well speci®ed under a variety of conditions. The wide acceptance of
OLS estimation may be attributed to the ease of estimation, its underlying capital asset
pricing theory, and that it provides the best unbiased estimator under the condition of