High dimensional minimum variance portfolio estimation under statistical factor models

We propose a high dimensional minimum variance portfolio estimator under statistical factor models, and show that our estimated portfolio enjoys sharp risk consistency. Our approach relies on properly integrating l(1) constraint on portfolio weights with an appropriate covariance matrix estimator. In terms of covariance matrix estimation, we extend the theoretical results of POET (Fan et al., 2013) to a setting that is coherent with principal component analysis. Simulation and extensive empirical studies on S&P 100 Index constituent stocks demonstrate favorable performance of our MVP estimator compared with benchmark portfolios. (C) 2020 Elsevier B.V. All rights reserved.

Automated summary

The study introduces a high-dimensional minimum variance portfolio estimator under statistical factor models, which achieves sharp risk consistency by integrating L(1) constraint on portfolio weights with an appropriate covariance matrix estimator. Empirical studies demonstrate the favorable performance of the estimator on S&P 100 Index constituent stocks compared to benchmark portfolios.