Correspondence: Timothy Adler, Windham Capital Management, LLC, 5 Revere Street, Cambridge, MA 02138, USA. Tel: +1 617 234 9459; Fax: +1 617 576 7360; E-mail: tadler@windhamcapital.com

¹is vice president of research and development. He manages the development of Windham Portfolio Advisor™ investment technology and overseas research and development of IT-based tools and strategies to support our advisory and asset management service. Before his association with Windham, he was a member of the research group at State Street Associates, where he conducted portfolio construction and risk management analyses. He received Bachelor of Computer Systems Engineering and Bachelor of applied Computer Science degrees from the Royal Melbourne Institute of Technology and a Master of Business Administration degree from the Carroll Graduate School of Management at Boston College.

²is president and CEO of Windham Capital Management, LLC, where he is responsible for managing research activities and investment advisory services. He teaches a graduate course in financial engineering at MIT's Sloan School of Management. He serves on several corporate and non-profit boards, including the Institute for Quantitative Research in Finance, the International Securities Exchange, and State Street Associates. He is a member of several advisory and editorial boards, including Emerging Markets Review, Financial Analysts Journal, the International Association of Financial Engineers, the Journal of Alternative Investments, the Journal of Derivatives, and the Journal of Investment Management, where he is Book Review editor. He won Graham and Dodd awards in 1993 and 2002, the Research Prize from the Institute for Quantitative Investment Research in 1997, and the Bernstein-Fabozzi/Jacobs-Levy Award in 2003. In 2004, he was elected a Batten Fellow at the Darden Graduate School of Business Administration, University of Virginia. He received a Master of Business Administration degree from the Graduate School of Business at New York University.

Received 9 May 2006.

Abstract

We present a recent innovation to portfolio construction called full-scale optimisation. In contrast to mean–variance analysis, which assumes that returns are normally distributed or that investors have quadratic utility, full-scale optimisation identifies the optimal portfolio given any set of return distributions and any description of investor preferences. It therefore yields the truly optimal portfolio in sample, whereas mean–variance analysis provides an approximation to the in-sample truth. Both approaches, however, suffer from estimation error. We employ a bootstrapping procedure to compare the estimation error of full-scale optimisation to the combined approximation and estimation error of mean–variance analysis. We find that, to a significant degree, the in-sample superiority of full-scale optimisation prevails out of sample.