Extreme Value Estimation of Boom and Crash Statistics

Extreme price movements associated with market crashes and booms have catastrophic repercussions for all investors and it is necessary to make accurate predictions of the frequency and severity of these events. This paper investigates the extreme behaviour of equity market returns and quantifies the possible losses experienced during financial crises. Extreme value theory using the block maxima method is applied to equity indices representing American, Asian and European markets. The empirical evidence shows that the tail indices are characterized by the fat-tailed Frechet distribution. Extreme return levels associated with market crashes are more severe than booms. Asian markets exhibit the largest propensity for experiencing crashes and booms.