Home > Research > Publications & Outputs > Beyond GMV

Electronic data

  • beyondgmv_nonblind_main

    Accepted author manuscript, 385 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Beyond GMV: the relevance of covariance matrix estimation for risk-based portfolio construction

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Beyond GMV: the relevance of covariance matrix estimation for risk-based portfolio construction. / Dom, M.S.; Howard, C.; Jansen, M. et al.
In: Quantitative Finance, Vol. 25, No. 3, 31.03.2025, p. 403-419.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Dom MS, Howard C, Jansen M, Lohre H. Beyond GMV: the relevance of covariance matrix estimation for risk-based portfolio construction. Quantitative Finance. 2025 Mar 31;25(3):403-419. Epub 2025 Mar 7. doi: 10.1080/14697688.2025.2468268

Author

Dom, M.S. ; Howard, C. ; Jansen, M. et al. / Beyond GMV : the relevance of covariance matrix estimation for risk-based portfolio construction. In: Quantitative Finance. 2025 ; Vol. 25, No. 3. pp. 403-419.

Bibtex

@article{e3b445f806a742beb216806545dda6b1,
title = "Beyond GMV: the relevance of covariance matrix estimation for risk-based portfolio construction",
abstract = "We empirically analyze the relevance of variance-covariance (VCV) estimators in equity portfolio construction. While traditional analyses of unconstrained global minimum-variance (GMV) portfolios support using shrinkage and modeling covariance dynamics, the resulting portfolios are often impractical due to high leverage, concentration, and costs. By examining constrained GMV and risk parity portfolios, we find a significantly reduced opportunity for alternative VCV estimators to outperform the sample estimator. Specifically, we show that a long-only portfolio with asset-level constraints and a transaction cost penalty produces similar results to shrinkage-based methods, even when using the sample VCV estimator. However, accounting for time-series dynamics in asset returns remains statistically relevant for volatility reduction. Our findings emphasize how the interaction between VCV estimators and portfolio construction choices shapes both the statistical and practical outcomes in portfolio management.",
author = "M.S. Dom and C. Howard and M. Jansen and H. Lohre",
year = "2025",
month = mar,
day = "31",
doi = "10.1080/14697688.2025.2468268",
language = "English",
volume = "25",
pages = "403--419",
journal = "Quantitative Finance",
issn = "1469-7688",
publisher = "Routledge",
number = "3",

}

RIS

TY - JOUR

T1 - Beyond GMV

T2 - the relevance of covariance matrix estimation for risk-based portfolio construction

AU - Dom, M.S.

AU - Howard, C.

AU - Jansen, M.

AU - Lohre, H.

PY - 2025/3/31

Y1 - 2025/3/31

N2 - We empirically analyze the relevance of variance-covariance (VCV) estimators in equity portfolio construction. While traditional analyses of unconstrained global minimum-variance (GMV) portfolios support using shrinkage and modeling covariance dynamics, the resulting portfolios are often impractical due to high leverage, concentration, and costs. By examining constrained GMV and risk parity portfolios, we find a significantly reduced opportunity for alternative VCV estimators to outperform the sample estimator. Specifically, we show that a long-only portfolio with asset-level constraints and a transaction cost penalty produces similar results to shrinkage-based methods, even when using the sample VCV estimator. However, accounting for time-series dynamics in asset returns remains statistically relevant for volatility reduction. Our findings emphasize how the interaction between VCV estimators and portfolio construction choices shapes both the statistical and practical outcomes in portfolio management.

AB - We empirically analyze the relevance of variance-covariance (VCV) estimators in equity portfolio construction. While traditional analyses of unconstrained global minimum-variance (GMV) portfolios support using shrinkage and modeling covariance dynamics, the resulting portfolios are often impractical due to high leverage, concentration, and costs. By examining constrained GMV and risk parity portfolios, we find a significantly reduced opportunity for alternative VCV estimators to outperform the sample estimator. Specifically, we show that a long-only portfolio with asset-level constraints and a transaction cost penalty produces similar results to shrinkage-based methods, even when using the sample VCV estimator. However, accounting for time-series dynamics in asset returns remains statistically relevant for volatility reduction. Our findings emphasize how the interaction between VCV estimators and portfolio construction choices shapes both the statistical and practical outcomes in portfolio management.

U2 - 10.1080/14697688.2025.2468268

DO - 10.1080/14697688.2025.2468268

M3 - Journal article

VL - 25

SP - 403

EP - 419

JO - Quantitative Finance

JF - Quantitative Finance

SN - 1469-7688

IS - 3

ER -