An Evaluation of Testing Procedures for Long Horizon Event Studies

The advantages of using quarterly returns for long-term event studies

“…We refer to those firms that have made information announcements as event or treatment firms and those firms selected for comparison as match [matching] or control firms and to this category of techniques as characteristic-based matching. As pointed out by Chou et al (2006Chou et al ( , 2010, Dichev and Piotroski (2001), Ang and Zhang (2004) and Byoun (2004) there is a lack of consensus on the best approach to select the comparison firm returns and to ascertain whether the abnormal returns generated using a particular firm or set of firms are statistically detectible at generally accepted levels. 3 In this paper, we propose and investigate tests for abnormal returns on quarterly nonoverlapping intervals that can be used for longer periods (up to 2 years) alone or in conjunction with the current long-term tests.…”

A Study of How Underperforming Firms Follow Industry Leaders When Adopting ERP Systems and the Economic Effects of Their Adoption Decisions

“…A better measure is the total returns that shareholders experience based on the change in price (capital appreciation) and dividends earned over a period of time. To test our hypotheses, we examine monthly returns for ERP adopters prior to the ERP implementation decision using the following abnormal returns model adapted from Ang and Zhang (2004):…”

Bad News Do Not Always Travel Slowly: The Bankruptcy Case

“…23 I also present median returns to check the validity of my parametric results. These returns are unaffected by extreme observations, and present some theoretical advantages over mean BHARs (Ang and Zhang, 2004). Drawing on previous research dealing with bankruptcy announcements, a Wilcoxon signed rank-test is employed to test the statistical significance of my median abnormal returns (Dawkins et al, 2007).…”

“…I employ a conventional t-test to infer the statistical significance of the mean BHAR (Barber and Lyon, 1997;Ang and Zhang, 2004). I use the cross-section of the buy-andhold abnormal returns to form an estimator of their variance (Boehmer, Musumeci and Poulsen, 1991) since previous research by Aharony, Jones and Swary (1980) shows that both the systematic and unsystematic risk of bankrupt firms changes as the bankruptcy date approaches.…”

“…As suggested by equation (4), I use equally weighted rather than value-weighted returns since this is more appropriate in the context under analysis (e.g., Gilson, 1995). A single control firm is used to proxy for the expected return of each of my sample firms Lyon, 1997 andAng andZhang, 2004). Following the recent literature exploring the market's reaction to public events when firms are financially distressed, benchmark firms are defined based on size and book-to-market ratio (Dichev and Piotroski, 2001;Taffler et al, 2004;Ogneva and Subramanyam, 2007;Kausar et al, 2009).…”