Estimation Methods in Portfolio Selection and the Effectiveness of Short Sales Restrictions: UK Evidence
比较了贝叶斯-斯坦因等八种估计方法在马克维茨模型中的表现，发现卖空限制能改善实际组合绩效，但各方法间差异不大。
Forecasting the mean returns vector and the covariance matrix is a key feature in implementing portfolio theory. The performance of the Bayes-Stein method for forecasting these parameters for use in the Markowitz model (with and without short sales) was compared with that of seven other estimation methods, and three alternative portfolio selection techniques. This paper represents the first large scale empirical investigation of the usefulness of the Bayes-Stein approach using historical data. This data was drawn from the London Stock Exchange. In contrast to earlier studies, the relative performance of Bayes-Stein was mixed. While it produced reasonable estimates of the mean returns vector, there were superior methods, e.g., overall mean, for estimating the covariance matrix when short sales were permitted. When short sales were prohibited, actual portfolio performance was clearly improved, although there was little to choose between the various estimation methods.