Improved Estimation of the Covariance Matrix of Stock Returns With an Application to Portfolio Selection

Olivier Ledoit and Michael Wolf

Abstract

This paper proposes to estimate the covariance matrix of stock returns by an optimally weighted average of two existing estimators: the sample covariance matrix and the single-index covariance matrix. This method is generally known as shrinkage, and it is standard in decision theory and in empirical Bayesian statistics. Our shrinkage estimator can be seen as a way to account for extra-market covariance without having to specify an arbitrary multi-factor structure. For NYSE and AMEX stock returns from 1972 to 1995, it can be used to select portfolios with significantly lower out-of-sample variance than a set of existing estimators, including multi-factor models.


The Matlab code for the estimator proposed in the paper is shrinkMarket.m. However, you can estimate the covariance matrix by a weighted average of the sample covariance matrix with any other structured estimator. Examples of other structures that are intuitively appealing but are not in the paper include: the diagonal covariance matrix and the two-parameter covariance matrix. The corresponding Matlab functions are: shrinkDiag.m and shrink2para.m respectively.


Journal of Empirical Finance, Volume 10, Issue 5, December 2003, pages 603-621


Download full paper (Acrobat PDF - 198KB)


Back to research page

Back to home page