We revisit the question whether commodities should be included in investors' portfolios. We employ for the first time a stochastic dominance efficiency (SDE) approach to construct optimal portfolios with and without commodities and we evaluate their comparative performance. SDE circumvents the necessity to posit a specific utility function to describe investor's preferences and it does not impose distributional assumptions on asset returns. We find that commodities provide diversification benefits both in-and out-of-sample. This evidence is stronger when commodity indices which mimic dynamic commodity trading strategies are used. We explain our results by documenting that commodity markets are segmented from the equity and bond markets.

No abstract

No abstract

No abstract

This study develops and implements methods for determining whether introducing new securities or relaxing investment constraints improves the investment opportunity set for all risk averse investors. We develop a test procedure for "stochastic spanning" for two nested portfolio sets based on subsampling and linear programming. The test is statistically consistent and asymptotically exact for a class of weakly dependent processes. A Monte Carlo simulation experiment shows good statistical size and power properties in finite samples of realistic dimensions. In an application to standard datasets of historical stock market returns, we accept market portfolio efficiency but reject two-fund separation, which suggests an important role for higher-order moment risk in portfolio theory and asset pricing. Supplementary materials for this article are available online.