摘要：The objective of this paper was to compare and to analyze three portfolio selection models: Mean-Variance, Minimax and Minimax Weighted. These models were evaluated using historical data (September 1999 to August 2000, January 2001 to December 2001 and February 2002 to January 2003) obtained from the Brazilian Stock Market (Bovespa). They were selected optimal portfolios to each month based on the returns of the last twelve months. The results show that the returns obtained through the Mean-Variance model were superiors in certain circumstances and inferiors in others when compared to the Ibovespa index. The Minimax model obtained the best accumulated returns when compared with the others models and the Ibovespa index.
关键词：Portfolio selection;Mean-variance;Bovespa;Game theory
