Let's break down each of these concepts related to event studies in finance.
What is Event Studies?
Event studies are a quantitative research method used in finance to measure the impact of a specific
event (e.g., a merger announcement, earnings release, or regulatory change) on the market value of a
firm or a portfolio of firms. The core idea is to isolate the effect of the event from the general market
movements by comparing the actual returns of the affected firm(s) to what their returns would have
been *in the absence* of the event. This allows researchers to assess whether the event had a
statistically significant impact on the firm's stock price. Examples of events studied include:
• Mergers and Acquisitions: To see if the market values the deal positively or negatively.
• Earnings Announcements: To gauge the market's reaction to the reported performance.
• Dividend Changes: To determine how investors react to alterations in dividend payouts.
• Regulatory Changes: To assess the impact of new rules or laws on specific industries.
What is Event Study Methodology?
The methodology generally follows these steps:
1. Event Definition: Clearly define the event and its announcement date. This is crucial for consistency
and accuracy.
2. Sample Selection: Identify the firms affected by the event. This might involve a single firm or a group
of firms in the same industry. A control group of similar, but unaffected firms might also be selected.
3. Estimation Period: Choose a period *before* the event to estimate the firm's normal return. This
"estimation window" is used to model the firm's return behavior in the absence of the event. This
estimation uses market models such as the Capital Asset Pricing Model (CAPM) or the Fama-French
three-factor model.
4. Event Window: Define a period *around* the event date to measure the abnormal returns. This
window typically includes several days or weeks before and after the announcement.
5. Measuring Abnormal Returns: Calculate the difference between the firm's actual return and its
expected return during the event window (discussed in detail below).
6. Statistical Tests: Conduct statistical tests (parametric or non-parametric) to determine if the average
abnormal return during the event window is statistically significant. This helps determine if the event
had a real impact, or if the observed changes were just random fluctuations.
7. Interpretation: Analyze the results and draw conclusions about the market's reaction to the event.
What is Measuring Abnormal Returns?
Abnormal return is the difference between a security's actual return and its expected return. The
expected return is typically calculated using a market model. Common models include:
• Capital Asset Pricing Model (CAPM): Expected return = Risk-free rate + Beta * (Market return - Risk-
free rate)
• Fama-French Three-Factor Model: A more sophisticated model that accounts for size and value
factors in addition to market risk.
The abnormal return for a single day, *AR<sub>it</sub>*, for firm *i* on day *t* is:
*AR<sub>it</sub> = R<sub>it</sub> - E(R<sub>it</sub>)*
Where:
• R<sub>it</sub> is the actual return of firm *i* on day *t*
• E(R<sub>it</sub>) is the expected return of firm *i* on day *t*, estimated using a market model.
The cumulative abnormal return (CAR) sums the abnormal returns over the event window:
*CAR = Σ AR<sub>it</sub>* (summed over the event window)
What are Parametric and Non-parametric tests?
These are statistical tests used to determine if the average abnormal return is significantly different from
zero. The choice between them depends on the assumptions you're willing to make about the data.
• Parametric Tests: These tests assume the data follows a specific probability distribution (e.g., normal
distribution). Common parametric tests used in event studies include the *t-test* and other tests based
on li
