To what extent is resampling useful in portfolio management?

Abstract

We take a new look at the resampled efficiency^TM technique developed by Michaud (1998) and compare it with the Markowitz mean–variance portfolio construction technique by assessing the performance of three representative portfolios, i.e. the Global Minimum Variance (GMV) portfolio, the Intermediate Return (I) portfolio and the Maximum Return (M) portfolio. We show that resampling leads to more stable and more diversified portfolios. However, the out-of-sample analysis shows that resampling does not systematically increase (decrease) the risk adjusted performance (turnover) of the portfolios.

Acknowledgement

The authors thank BNP Paribas Fortis for their suggestions and comments as well as for welcoming one of the co-authors in a dynamic and friendly atmosphere in Brussels.

Notes

¹Resampled efficiency optimization was co-invented by Richard Michaud and Robert Michaud, US patent 6,003,018. New Frontier Advisors, LLC (NFA) is an exclusive worldwide licensee.