The Event Study

Methodology Since 1969

1
Contents

 Introduction
 Measurement and statistical analysis of abnormal returns
 Benchmark models of the normal return
 The statistical power of event studies
 Measurement and statistical analysis of abnormal returns modeled as
regression coefficients
 Summary

2
Introduction

 The event study methodology has used

 To examine security price behavior around events such as accounting rule changes,
earnings announcements, changes in the severity of regulation and money supply
announcements.
 Become the standard method of measuring security price reaction to some
announcement or event.
 In practice, event studies have been used for two major reasons:
 To test the null hypothesis that the market efficiently incorporates information
 To examine the impact of some event on the wealth of the firm’s security holders.

3
Introduction

 The author objective:

 To highlight the various extensions of the original FFJR technique and related
contributions that have appeared since 1969
 The paper is organized into two topics:
 Discusses the case where abnormal returns are measured as residuals from some
benchmark model of normal returns.
 Discusses the use of dummy variables, corresponding to the event period(s), in a
regression framework to parameterize the effects of the event.

4
Fama, Fisher, Jensen and Roll (1969)

 FFJR examine the effect of the announcement of a stock split on stock prices.
 They estimate the parameters of the following “market” model for each stock
i in the sample

5
Fama, Fisher, Jensen and Roll (1969)…
CONT
 The estimator of the average abnormal return during month s, AARs, is
defined as

 AARs summed across months to measure the average cumulative effect on the
sample securities of company specific information
 CAARS1,S2, the estimator of the cumulative average abnormal return, is given
by

6
Fama, Fisher, Jensen and Roll (1969)…
CONT
 Two modifications to the FFJR methodology have become standard.
1. It has become commonplace for studies with monthly observations to use 5 to 7
years of data.
2. If the event period is included in the period used to estimate the market model
parameters, the coefficient estimates are biased because the disturbances are
not mean zero.
 Scholes (1972) assumed that the coefficients are constant during the estimation and event
periods

7
Hypothesis testing

 Due to the fact that frequently the abnormal return estimators are not
independent or they do not have identical variance.
 There are several potential problems in hypothesis testing, The abnormal
return estimators
1. are cross sectionally ,in event time, correlated
2. Have different variances across firms
 Noted by Jaffe (1974) and Mandelker (1974). Fama (1976)

3. are not independent across time for a given firm

4. have greater variance during the event period than in the surrounding periods.

8
Hypothesis testing … CONT

 Binder (1998) conclude that those potential statistical problems are all could
be solved.
 For example cross-sectional dependence
 is not a problem when the event periods are randomly dispersed through calendar
time.
 will be a minor problem when event time is the same as calendar time but
securities are randomly chosen (from different industries) and market model
abnormal return estimates are used

9
Cross-sectional regression analysis

 Frequently the estimated abnormal returns for the sample firms are used as
the dependent variable in a regression with firm specific variables on the
right hand side.
 The disturbances in this regression may be heteroskedastic and correlated if
the abnormal return estimators have these properties. Gonedes and Dopuch
(1974)
 Solution to this problem
 is to use the estimated standardized average abnormal return for each calendar
month t. Jaffe (1974)
 The average value of each explanatory variable is weighted by dividing the
observations by the estimated standard deviation of the AARt.

10
Benchmark models of the normal
return
Abnormal returns have been measured

3. Mean-adjusted returns
 are calculated by subtracting the average return for stock i during the estimation
period from the stock’s return during the event period s.

4. Market-adjusted returns
 The market-adjusted return subtracts Rms from Ris.
 No statistical parameters are estimated.

11
Benchmark models of the normal
return…CONT
3. The market model approach
 Parameters are estimated using a pre-event period sample with ordinary least squares regression.
 The parameter estimates and the event period stock and market index returns are then used to estimate the
abnormal returns.
 This method controls for the risk (market factor beta) of the stock and the movement of the market during
the event period

12
Benchmark models of the normal
return…CONT
3. Deviations from the one factor
 When an equilibrium model such as the Sharpe-Lintner or Black (1972) CAPM is the
true process determining expected returns, the intercept in the market model
return generating process becomes
 where R0t is the riskless interest rate (in the Sharpe-Lintner version) or the expected
return on the zero beta portfolio (in the Black model). When R0t varies over time,
abnormal returns measured as CAPM prediction errors control for these changes
since only beta is estimated during the estimation period

13
Benchmark models of the normal
return…CONT
5. Multifactor model, such as the Arbitrage Pricing Theory (APT)
 Those where realized returns are a function of two or more variables (excluding
the zero beta return), can be divided into two types:
 Where the risks associated with the factors beyond the market return are presumed to
be priced (rewarded) by the market
 where they are not priced.

14
The statistical power of event studies

 Known event dates

 Brown and Warner (1980) conduct an extensive examination of event study techniques with monthly
return data from CRSP.
 Dyckman, Philbrick and Stephan (1984) and Brown and Warner (1985) similarly examine the usefulness of
the event study methodology when daily stock returns are used.
 These studies find that the different abnormal return measures perform similarly with daily return data
 Unknown event dates
 Simulated events.
 leakage of information, merger may be announced
 Actual events.
 Regulatory events where the event date is not known.

15
Modeling abnormal returns

 When there is one event

 Instead of using the model as prediction errors, the sample period can be extended to contain the event
period and a zero-one variable Dt can be included in the return equation

 When there are multiple events

 One dummy variable that equals one during each event period could be used
 CAPM could be used as the benchmark rather than the market model.
 The market model could be extended to control for the “January Effect” in security returns and to allow the beta
(and alpha) to change because of the event.

16
Modeling abnormal returns

 When abnormal returns differ in sign

 This asymmetry can be modeled into a multivariate regression model (MVRM)
system of return equations with one equation for each of the N firms (securities)
experiencing the A events

17
Statistical issues and hypothesis testing

 The standard error of the abnormal return estimator in simple or

multivariate regression is more than just the residual standard deviation
because it also depends on the estimation error in the other parameters.
 The real advantage of the MVRM framework over the standard
methodology lies in its ability to allow the abnormal returns to differ
across firms, including in sign, and to easily test joint hypotheses about
the abnormal returns

18
Summary

 The event study methodology it has been widely used in corporate finance beginning with FFJR in
1960s.
 These studies concluded that the market model works well as a measure of the benchmark rate of
return.
 Researchers have developed a number of solutions to a variety of statistical issues concerning the
variability and coverability of the abnormal return problems.
 Leading ultimately to unbiased and powerful tests of hypotheses about the average effect of the
event on the sample firms.
 Recently, studies modeling the abnormal returns as coefficients directly in a regression
framework.
 Multivariate regression model allows testing of several hypotheses.

19
Thanks

20