Multiperiod portfolio allocation: A study of volatility clustering, non-normalities and predictable returns

Abstract

This paper examines the dynamic, multiperiod portfolio choices of an investor facing predictable returns with volatility clustering and non-normalities, two pervasive stock return data characteristics. With a portfolio of one risk-free and one risky asset, we calibrate the model to the U.S. stock market and consider multiperiod choices, GARCH volatilities and Johnson-distributed non-normal errors. Quadrature techniques are used to determine the optimal allocation of the risky asset. The results show that accounting for volatility clustering strongly reduces the large hedging demands typically obtained with predictable returns. Non-normalities have modest impacts on allocations. Out-of-sample tests reveal that despite the changes in allocation observed in many cases, little statistical evidence is found that the Certainty Equivalent returns are impacted by multiperiod portfolios, nor by portfolios based on non-normal error.