On the statistical significance of the event effect on unsystematic volatility and returns

The methodology for determining the statistical significance of the impact of a certain event (stock split, corporate restructuring, change in regulation, etc.) on the unsystematic volatility of asset returns is developed. The measures of such an impact and corresponding test statistics are derived. Simulations show that the suggested tests reject the true null hypothesis of no impact on volatility at the levels equal to the significance of the test, while the rejection rates of false H 0 increase with the magnitude of the effect. Moreover, by utilizing the information on the stochastic behavior of the volatility, more powerful tests of the impact of a certain event on assets' unsystematic returns are developed. The proposed tests result in 9--17% higher rates of rejection of the false null hypothesis of no effect on returns than the rejection rates of the pre-existing tests. At the same time, the true null is rejected at the correct levels. In addition, the proposed test accommodates well the event-induced change in variance of asset returns. An application of the methodology to corporate spin-offs reveals statistically significant and long-lasting increases in unsystematic volatility of parent companies' returns.