Event Study (CAR and BHAR)
Also known as: event study, cumulative abnormal return analysis, abnormal return analysis, CAR, BHAR, Olay Çalışması (Event Study — CAR, BHAR)
The event study is a financial research method that measures the impact of a news release, policy change, or corporate event on asset prices through cumulative abnormal returns. Reviewed by MacKinlay (1997) and formalised econometrically by Kothari and Warner (2007), it is the standard tool for testing the efficient-market hypothesis and analysing the information content of events.
Key highlights
- Directly isolates the price impact of a specific dated event by netting out normal expected returns.
- The standard, widely accepted tool for testing market efficiency and the information content of events.
- Flexible across horizons: CAR for short windows and BHAR for long-run effects.
Intuition
This section is available to Pro members. Upgrade to Pro
How it works
This section is available to Pro members. Upgrade to Pro
When to use it
Use an event study when you want to quantify how a dated event — an earnings announcement, merger, regulatory ruling, or macro shock — affects asset prices, with at least about 30 observations and time-series return data. It assumes the normal (expected) return can be estimated from a market model or factor model, that event windows do not overlap (overlapping events must be combined), that cross-sectional correlation is handled via a test such as Boehmer's standardised cross-sectional test, and that long-horizon BHAR studies use a reference portfolio or control-firm matching.
Strengths & limitations
- Directly isolates the price impact of a specific dated event by netting out normal expected returns.
- The standard, widely accepted tool for testing market efficiency and the information content of events.
- Flexible across horizons: CAR for short windows and BHAR for long-run effects.
- Results depend heavily on the chosen normal-return benchmark (market model versus Fama-French factors).
- Overlapping or clustered events bias inference unless they are combined or corrected for cross-sectional correlation.
- Long-horizon BHAR is sensitive to the choice of reference portfolio or control firm and to compounding.
Common pitfalls
This section is available to Pro members. Upgrade to Pro
Applications
This section is available to Pro members. Upgrade to Pro
Frequently asked
What is the difference between CAR and BHAR?
CAR (cumulative abnormal return) sums daily abnormal returns over a short event window, making it suited to immediate reactions. BHAR (buy-and-hold abnormal return) compounds returns and subtracts the compounded return of a matched reference portfolio, making it suited to long-horizon effects but more sensitive to the benchmark choice.
How is the expected (normal) return estimated?
It is predicted from a benchmark model fitted on a pre-event estimation window — most commonly the market model or the Fama-French factor model. The abnormal return is then the actual return minus this expected return.
Why does cross-sectional correlation matter?
When events cluster in calendar time, abnormal returns across firms are correlated, so naive t-tests overstate significance. The Boehmer standardised cross-sectional test corrects for this so that the inference remains valid.
What should I do about overlapping event windows?
Overlapping windows contaminate the abnormal returns of nearby events. Events that occur close together should be combined, and clustering should be addressed through a cross-sectional correlation correction.
Sources
- 1.MacKinlay, A. C. (1997). Event Studies in Economics and Finance. Journal of Economic Literature, 35(1), 13–39.
- 2.Kothari, S. P., & Warner, J. B. (2007). Econometrics of Event Studies. In B. E. Eckbo (Ed.), Handbook of Corporate Finance: Empirical Corporate Finance (Vol. 1, pp. 3–36). Elsevier.
You have read it. What now?
Cite this page
ScholarGate. (2026, June 1). Event Study. ScholarGate. https://scholargate.app/finance/event-study-finance