DeepAI AI Chat
Log In Sign Up

The Oracle estimator is suboptimal for global minimum variance portfolio optimisation

by   Christian Bongiorno, et al.

A common misconception is that the Oracle eigenvalue estimator of the covariance matrix yields the best realized portfolio performance. In reality, the Oracle estimator simply modifies the empirical covariance matrix eigenvalues so as to minimize the Frobenius distance between the filtered and the realized covariance matrices. This leads to the best portfolios only when the in-sample eigenvectors coincide with the out-of-sample ones. In all the other cases, the optimal eigenvalue correction can be obtained from the solution of a Quadratic-Programming problem. Solving it shows that the Oracle estimators only yield the best portfolios in the limit of infinite data points per asset and only in stationary systems.


page 1

page 2

page 3

page 4


An Orthogonally Equivariant Estimator of the Covariance Matrix in High Dimensions and Small Sample Size

An orthogonally equivariant estimator for the covariance matrix is propo...

Optimal shrinkage covariance matrix estimation under random sampling from elliptical distributions

This paper considers the problem of estimating a high-dimensional (HD) c...

Eigenvalue distribution of a high-dimensional distance covariance matrix with application

We introduce a new random matrix model called distance covariance matrix...

Minimum Eigenvalue Based Covariance Matrix Estimation with Limited Samples

In this paper, we consider the interference rejection combining (IRC) re...

Covariance matrix filtering with bootstrapped hierarchies

Statistical inference of the dependence between objects often relies on ...

Large Non-Stationary Noisy Covariance Matrices: A Cross-Validation Approach

We introduce a novel covariance estimator that exploits the heteroscedas...

Entropic Determinants

The ability of many powerful machine learning algorithms to deal with la...