A new stochastically flexible event methodology with application to Proposition 103

In this article, we developed a dynamic market model to obtain the expected returns of individual securities. This model takes into account certain known characteristics of financial time series, including time-varying beta, autocorrelated squared returns, and the fat-tailed property of daily return data. An autoregressive process with order 1, AR (1), is initialized for beta, and a GARCH (1,1) process is utilized to model the time-varying conditional variance. Our study suggests that the application of the classical event study methodology, without checking the behavior of security returns for stochastic beta and GARCH effects, may very well cause researchers to draw inappropriate conclusions.