Regularized semiparametric estimation of high dimensional dynamic conditional covariance matrices

被引：6
作者：
Morana, Claudio [1 ,2 ,3 ,4 ]
机构：
[1] Univ Milano Bicocca, Dipartimento Econ Metodi Quantitat & Strategie Im, Piazza Ateneo Nuovo 1, I-20126 Milan, Italy
[2] Univ Milano Bicocca, Ctr European Studies CefES Italy, Piazza Ateneo Nuovo 1, I-20126 Milan, Italy
[3] Coll Carlo Alberto, Ctr Res Pens & Welf Policies CeRP Italy, Piazza Vincenzo Arbarello 8, I-10122 Turin, Italy
[4] Rimini Ctr Econ Anal RCEA Canada, 75 Univ Ave W, Waterloo, ON N2L 3C5, Canada
来源：
ECONOMETRICS AND STATISTICS | 2019年 / 12卷
关键词：
Conditional covariance; Dynamic conditional correlation model; Semiparametric dynamic conditional correlation model; Multivariate GARCH; NONLINEAR SHRINKAGE; MULTIVARIATE; MARGINALIZATION; AGGREGATION; MODEL;
D O I：
10.1016/j.ecosta.2019.04.001
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
A three-step estimation strategy for dynamic conditional correlation (DCC) models is proposed. In the first step, conditional variances for individual and aggregate series are estimated by means of QML equation by equation. In the second step, conditional covariances are estimated by means of the polarization identity and conditional correlations are estimated by their usual normalization. In the third step, the two-step conditional covariance and correlation matrices are regularized by means of a new non-linear shrinkage procedure and optimally smoothed. Due to its scant computational burden, the proposed regularized semiparametric DCC model (RSP-DCC) allows to estimate high dimensional conditional covariance and correlation matrices. An application to global minimum variance portfolio is also provided, confirming that RSP-DCC is a simple and viable alternative to existing DCC models. (C) 2019 EcoSta Econometrics and Statistics. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码：42 / 65
页数：24
相关论文
共 50 条
  • [31] Dynamic Conditional Correlation: On Properties and Estimation
    Aielli, Gian Piero
    JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2013, 31 (03) : 282 - 299
  • [32] On the estimation of dynamic conditional correlation models
    Hafner, Christian M.
    Reznikova, Olga
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2012, 56 (11) : 3533 - 3545
  • [33] A Well-Conditioned and Sparse Estimation of Covariance and Inverse Covariance Matrices Using a Joint Penalty
    Maurya, Ashwini
    JOURNAL OF MACHINE LEARNING RESEARCH, 2016, 17
  • [34] Risk-Based Portfolios with Large Dynamic Covariance Matrices
    Nakagawa, Kei
    Imamura, Mitsuyoshi
    Yoshida, Kenichi
    INTERNATIONAL JOURNAL OF FINANCIAL STUDIES, 2018, 6 (02):
  • [35] Cleaning large-dimensional covariance matrices for correlated samples
    Burda, Zdzislaw
    Jarosz, Andrzej
    PHYSICAL REVIEW E, 2022, 105 (03)
  • [36] High dimensional covariance matrix estimation by penalizing the matrix-logarithm transformed likelihood
    Yu, Philip L. H.
    Wang, Xiaohang
    Zhu, Yuanyuan
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2017, 114 : 12 - 25
  • [37] High-Dimensional Learning of Linear Causal Networks via Inverse Covariance Estimation
    Loh, Po-Ling
    Buehlmann, Peter
    JOURNAL OF MACHINE LEARNING RESEARCH, 2014, 15 : 3065 - 3105
  • [38] A Conditional l1 Regularized MMSE Channel Estimation Technique for IBI Channels
    Takano, Yasuhiro
    Su, Hsuan-Jung
    Juntti, Markku
    Matsumoto, Tad
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2018, 17 (10) : 6720 - 6734
  • [39] Eigenvalue Estimation of Hyperspectral Wishart Covariance Matrices From Limited Number of Samples
    Ben-David, Avishai
    Davidson, Charles E.
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2012, 50 (11): : 4384 - 4396
  • [40] ESTIMATION OF (NEAR) LOW-RANK MATRICES WITH NOISE AND HIGH-DIMENSIONAL SCALING
    Negahban, Sahand
    Wainwright, Martin J.
    ANNALS OF STATISTICS, 2011, 39 (02) : 1069 - 1097
12345