28.7 Heterogeneity in the event effect

\[ y = X \theta + \eta \]


  • \(y\) = CAR

  • \(X\) = Characteristics that lead to heterogeneity in the event effect (i.e., abnormal returns) (e.g., firm or event specific)

  • \(\eta\) = error term


  • In cases with selection bias (firm characteristics and investor anticipation of the event: larger firms might enjoy great positive effect of an event, and investors endogenously anticipate this effect and overvalue the stock), we have to use the White’s \(t\)-statistics to have the lower bounds of the true significance of the estimates.
  • This technique should be employed even if the average CAR is not significantly different from 0, especially when the CAR variance is high (Boyd, Chandy, and Cunha Jr 2010)

28.7.1 Common variables in marketing

(A. Sorescu, Warren, and Ertekin 2017) Table 4

  • Firm size is negatively correlated with abnormal return in finance (A. Sorescu, Warren, and Ertekin 2017), but mixed results in marketing.

  • # of event occurrences

  • R&D expenditure

  • Advertising expense

  • Marketing investment (SG&A)

  • Industry concentration (HHI, # of competitors)

  • Financial leverage

  • Market share

  • Market size (total sales volume within the firm’s SIC code)

  • marketing capability

  • Book to market value

  • ROA

  • Free cash flow

  • Sales growth

  • Firm age


Boyd, D Eric, Rajesh K Chandy, and Marcus Cunha Jr. 2010. “When Do Chief Marketing Officers Affect Firm Value? A Customer Power Explanation.” Journal of Marketing Research 47 (6): 1162–76.
Sorescu, Alina, Nooshin L Warren, and Larisa Ertekin. 2017. “Event Study Methodology in the Marketing Literature: An Overview.” Journal of the Academy of Marketing Science 45: 186–207.