Minimising Operational Risk in Portfolio Allocation Decisions

19 Pages Posted: 11 Jan 2007 Last revised: 20 Jan 2009

Date Written: January 13, 2008

Abstract

Models play an important role in strategic asset allocation (SAA), however by too much trust in the model stability, results are typically not so useful for practitioners. Professionals usually face the challenging problem of choosing a SAA model that matches their goals, bearing the operational risk of wrong choice (the model risk). Looking for helping them, this paper evaluates several methodologies of estimating efficient portfolios, under the perspective of global long-term investor, and also presents an approach (RATE) to incorporate estimation risk into mean-variance portfolio selection, based on the portfolio resampling technique. Our results support the use of the Michaud (1998) resampling methodology followed by the RATE, as they offer better results in terms of financial efficiency, allocation stability and diversification. In our evaluation of the different models we used several international asset classes for a period from June 1998 to July 2006. The findings are very useful for practitioners who can benefit from a fairly simple and robust asset allocation methodology.

Keywords: Model risk; Estimation risk, Portfolio Optimisation

JEL Classification: G11, G15, G23

Suggested Citation

Fernandes, Jose Luiz Barros and Ornelas, Jose Renato Haas, Minimising Operational Risk in Portfolio Allocation Decisions (January 13, 2008). Available at SSRN: https://ssrn.com/abstract=955861 or http://dx.doi.org/10.2139/ssrn.955861

Jose Luiz Barros Fernandes (Contact Author)

Universidade de Brasília ( email )

Campus Universitário Darcy Ribeiro
Brasília, Distrito Federal 70910-900
Brazil

Jose Renato Haas Ornelas

Banco Central do Brasil ( email )

P.O. Box 08670
SBS Quadra 3 Bloco B - Edificio-Sede
Brasilia, Distrito Federal 70074-900
Brazil

HOME PAGE: http://www.bcb.gov.br

Register to save articles to
your library

Register

Paper statistics

Downloads
402
Abstract Views
1,754
rank
73,063
PlumX Metrics