Auke Plantinga

Search this site

Event Studies


Contents

  1. 1 Introduction 
  2. 2 Data
  3. 3 Methodology
  4. 4 Requirements for papers/presentations that you need to hand in during class
  5. 5 References to papers on event study methodology
  6. 6 Literature
  7. 7 Webistes

Introduction 

This website is a source of information for students who want to perform an event study in Finance as part of a Bachelor or a Master thesis. It is written for students of the University of Groningen. In finance, event study methodology is a popular tool for investigating the impact of events on stock returns. 
 

Data

Information on stock returns can be obtained from Thomson's Datastream. However, there are several attractive alternatives. Consider for example Yahoo Finance, where you can find a lot of information on US stocks.
 
We also maintain a page with links to datasources, including databases with events:
 

Data sources

Web addressDescriptionType
International Disaster Database Database of world wide disasters Events 
Zephyr Mergers and acquisitions Events 
US Consumer Product & Safety Commision Official US govenment website on product recalls and safety issues with consumer goods Events 
http://www.ukrecallnotice.co.uk/ Product safety recalls for the United Kingdom Events 
http://www.sec.gov/ Supervisor of US securities markets provides a lot of information suitable for study in a Bachelor or Master thesis Events 
www.recalls.gov US Government database with lots of information on recalls in convenient database format Events 
Pacific Exchange Rate Service Sauder School of Business provides historical exchange rates starting from 1971 for most currencies. Exchange rates 
Groningen Growth and Development Centre Historical macro economic data Macro Data 
Showing 8 items from page Datasources sorted by Type, Description. View more »
 
 

Methodology

Event studies are designed to measure the impact on a security's return of a particular event type. In doing so, we calculate the return on the date of the event or the date that the event became known to the general public. Next, we control for the normal return on the event date by the benchmark or normal returns. 
 
In order to test whether abnormal returns exist on a particular event day, we calculate the following test statistic:

where CAR(t1,t2) represents the average cumulative abnormal return of all observations in the event window (t1,t2). This test statistic has a normal distribution and the observations are assumed to be independent.
 
In order to apply this test statistic, we need to check whether abnormal returns indeed have a normal distribution and whether the observations are independent. Checking for normality can be done with the Jarcque-Bera test. If the abnormal returns do not follow a normal distribution, you may consider using the Corrado (1989) test, which is a non-parametric test. The Corrado test ranks the return(s) in the event window relative to the period including both the estimation window and the event window. The Corrado test includes the following test statistic:

See the attached excel sheet on how to implement the Corrado test. The next figure is a screenshot of this spreadsheet. It provides data on 3 different stocks, with an estimation window of 5 days and an event window of 1 day. For each stock, we transform the abnormal returns in ranks (use the RANK command) for each day. For example, for stock 1, the lowest return was on day -5, which therefore has a rank of 1. The average excess ranking on day 0 was 2.5, and the question is whether this excess ranking is statistically signficant given the variation over time in average excess rankings. The standard deviation of the average daily rankings are present in Cell I15, which shows us a value of 1.41. As a result, the value of the test statistic (presented in Cell I4) equal 2.5/1.41 = 1.77.


It is not uncommon that the outcomes of the Corrado test are not different from the standard test. If that happens, you may consider presenting the Corrado test as a robustness check and report it in a section 'Robustness checks' after the main results. Announcements are clustered if (some of the) event windows of the observations overlap. With clustered observations, the announcement are no longer independent. 

Quite often, you may need to use multi-period event windows. Kolari and Pynnonen (2010) provide clues how to apply rank tests such as the Corrado test in that case.
 

Requirements for papers/presentations that you need to hand in during class

  1. Class 1
  2. Class 2
  3. Class 3
  4. Class 4
  5. Class 5
  6. General requirements
  7. Checklist

References to papers on event study methodology

  • Barber, Brad M., and John D. Lyon, 1997, ‘Detecting long-run abnormal stock returns: The empirical power and specification of test statistics’, Journal of Financial Economics, Vol. 43, pp. 341-372.
  • Brown, S.J., and J.B Warner, 1980, ‘Measuring security price performance’, Journal of Financial Economics, Vol. 8, pp. 205-258.
  • Brown, S.J., and J.B. Warner, 1985, ‘Using daily stock returns: the case of event studies’, Journal of Financial Economics, Vol. 14, pp. 3-31.
  • Corrado, Charles, 1989, ‘A nonparametric test for abnormal security-price performance in event studies’, Journal of Financial Economics, Vol. 23, No. 2, pp. 385-395.
  • Kolari, James W., and Seppo Pynnonen, 2010, 'Nonparametric Rank Tests for Event Studies', SSRN Working Paper.
  • Kothari, S.P., and Jerold B. Warner, 1997, ‘Measuring long-horizon security price performance’, Journal of Financial Economics, Vol. 43, pp. 301-339.
  • Kothari, S.P. and Jerold B. Warner, 2006, ‘Econometrics of Event Studies’, In: Handbook of Corporate Finance: Empirical Corporate Finance, Ed. B. Espen Eckbo.
  • MacKinlay, A. Craig, 1997, ‘Event studies in economics and finance’, Journal of Economic Literature, Vol. 35, No.1 , pp. 13-39.

 

Literature

In writing your thesis, it is important to acquaint yourself with the research that has been done in the field before. The leading journals in Finance are:

  • Journal of Finance
  • Journal of Financial Economics
  • Review of Financial Studies

The leading journals have a strong focus on the US. Other journals that publish research in finance (and in particular with a more European focus) are:

  • Journal of Banking and Finance
  • Journal of Business, Finance, and Accounting
  • Financial Management

Webistes




Subpages (5): Datastream Files General requirements Normal returns Results