Positive-definite modification of a covariance matrix by minimizing the matrix l(infinity) norm with applications to portfolio optimization
- Authors
- Cho, Seonghun; Katayama, Shota; Lim, Johan; Choi, Young-Geun
- Issue Date
- Dec-2021
- Publisher
- SPRINGER
- Keywords
- High-dimensional covariance matrix; Linear shrinkage; Matrix l(infinity) norm; Minimum variance portfolio; Positive definiteness; Regularized covariance matrix estimator
- Citation
- ASTA-ADVANCES IN STATISTICAL ANALYSIS, v.105, no.4, pp 601 - 627
- Pages
- 27
- Journal Title
- ASTA-ADVANCES IN STATISTICAL ANALYSIS
- Volume
- 105
- Number
- 4
- Start Page
- 601
- End Page
- 627
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/146090
- DOI
- 10.1007/s10182-021-00396-7
- ISSN
- 1863-8171
1863-818X
- Abstract
- The covariance matrix, which should be estimated from the data, plays an important role in many multivariate procedures, and its positive definiteness (PDness) is essential for the validity of the procedures. Recently, many regularized estimators have been proposed and shown to be consistent in estimating the true matrix and its support under various structural assumptions on the true covariance matrix. However, they are often not PD. In this paper, we propose a simple modification to make a regularized covariance matrix be PD while preserving its support and the convergence rate. We focus on the matrix l(infinity) norm error in covariance matrix estimation because it could allow us to bound the error in the downstream multivariate procedure relying on it. Our proposal in this paper is an extension of the fixed support positive-definite (FSPD) modification by Choi et al. (2019) from spectral and Frobenius norms to the matrix l(infinity) norm. Like the original FSPD, we consider a convex combination between the initial estimator (the regularized covariance matrix without PDness) and a given form of the diagonal matrix minimize the l(infinity) distance between the initial estimator and the convex combination, and find a closed-form expression for the modification. We apply the procedure to the minimum variance portfolio (MVP) optimization problem and show that the vector l(infinity) error in the estimation of the optimal portfolio weight is bounded by the matrix l(infinity) error of the plug-in covariance matrix estimator. We illustrate the MVP results with S&P 500 daily returns data from January 1978 to December 2014.
- Files in This Item
-
- Appears in
Collections - 이과대학 > 통계학과 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.