Estimation risk versus optimality risk: An ex-ante efficiency analysis of alternative equity portfolio diversification strategies

Implementing portfolio optimization techniques in practice is a challenging task because of the presence of estimation risk for the required parameters, namely expected returns and covariances. This paper provides a detailed empirical analysis of the trade-off between estimation risk, i.e., the risk of imperfect estimation for the required risk and return parameters, and optimality risk, the risk induced by investing in a heuristic portfolio strategy (e.g., an equally-weighted scheme) that requires fewer or no parameter estimates. Formally, we measure the opportunity costs related to estimation risk and optimality risk as the difference in ex-ante Sharpe ratios between the true maximum Sharpe ratio portfolio and the benchmark used in practice, which is plagued by the presence of estimation risk and/or optimality risk.