Alternative Models for the Conditional Heteroskedasticity of Stock Returns: Evidence from Deposit Institutions

The interest shown in the study of the volatility of asset prices has been considerable for several years. In an important paper, Merton (1980) pointed out that a weakness of a significant number of empirical studies of asset returns is the failure to account for the effect of changes in the level of risk when estimating expected returns. He further pointed out that estimators which use ex‐post returns should take account of heteroscedasticity. He concluded that one of the most important directions for future research is to develop accurate variance estimation models which take account of the errors in variance estimation. The development of autoregressive conditional heteroscedasticity (ARCH) by Engle (1982) and the generalized ARCH (GARCH) by Bollerslev (1986) has provided financial economists with a model for returns which specifically allows for changing conditional variances. In this paper I apply ARCH modeling strategy to study the relationship between risk and returns of deposit institutions.