Markowitz versus Regime Switching: An Empirical Approach

This article discusses an adjusted regime switching model in the context of portfoliooptimization and compares the attained portfolio weights and the performance to aclassical mean-variance set-up as introduced by Markowitz (1952). The model postulatesdifferent asset price dynamics under different regimes, and jumps between regimes are drivenby a Markov process. For examples, ’bear’ and ’bull’ markets could be such regimes. Givena particular regime, portfolio weights are set based on the conditional means and variancecovariancestructure of the asset dynamics. The model is evaluated in an out-of-sampleperiod of the last three years with a moving window and a forecast of only one period. It isfound that with the adjusted regime switching portfolio selection algorithm as applied here,the performance of the optimal portfolio is highly improved even where portfolio weights areconstrained to realistic values.