Large portfolio optimisation approaches

This paper makes an empirical comparison of prominent methods in portfolio optimisation, such as nodewise regression, the sample covariance matrix, observable factor model-based covariance matrices, linear and nonlinear shrinkage methods, and principal orthogonal complement thresholding (POET) estim...

Full description

Saved in:
Bibliographic Details
Published in:Journal of asset management 2023-10, Vol.24 (6), p.485-497
Main Authors: Ulasan, Esra, Önder, A. Özlem
Format: Article
Language:English
Subjects:
Bull markets
Comparative analysis
Economics and Finance
Emerging markets
Finance
Financial Services
Original Article
Portfolio performance
Risk Management
Securities markets
Stock exchanges
Volatility
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper makes an empirical comparison of prominent methods in portfolio optimisation, such as nodewise regression, the sample covariance matrix, observable factor model-based covariance matrices, linear and nonlinear shrinkage methods, and principal orthogonal complement thresholding (POET) estimators. Empirically, we find that the nodewise regression approach that uses a direct estimator of the sparse inverse covariance matrix improves portfolio performance among existing methods in mean-variance portfolio optimisation when the number of stocks is greater than the number of observations.
ISSN:1470-8272
1479-179X
DOI:10.1057/s41260-023-00322-3