Improving Mean-Variance Portfolios with Skewness Optimization

Summary

This report summary reviews Markowitz portfolio theory and its mean-variance efficient frontier, then questions the normal-return assumption underlying variance as a complete measure of risk. Since observed asset returns can be sharply peaked and heavy-tailed, it proposes incorporating higher moments to represent return distributions more fully. A polynomial goal programming approach assigns weights to objectives such as expected return, variance, skewness, and kurtosis.

The reported comparison finds that adding skewness to the return and variance objectives improves the portfolio Sharpe ratio. The improvement is said to persist across different underlying assets, including stocks and commodities, and across different test periods. Adding kurtosis on top of skewness gives no clear further benefit, which the report attributes to the two-sided interpretation of extreme outcomes. The available text supplies no numerical performance results or detailed methodology, and the tests remain historical; the authors caution that changing market behavior can undermine both the original and modified models. The index samples also may not represent broader markets.

Key ideas

• Markowitz optimization constructs portfolios along an efficient frontier using expected return and variance.
• Variance alone may poorly describe returns when distributions are peaked and heavy-tailed.
• Polynomial goal programming can combine return, variance, skewness, and kurtosis objectives.
• The report says that including skewness improved Sharpe ratios across assets and test periods.
• Adding kurtosis produced no clear additional improvement, and historical findings may not persist.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.