The Next Best Thing to Knowing Someone Who is Usually Right

Abstract

Mean-variance analysis is widely used for portfolio allocation decisions. The use of historical data for the inputs may be inferior to using informed estimates that reflect one's beliefs about the current financial environment. In this article we show that portfolios based on expert opinion can outperform portfolios based on historical data, and that even better performance can be achieved by taking into account regression to the mean.

TOPICS: Portfolio construction, statistical methods, performance measurement