Gaussian fluctuations for sample covariance matrices with dependent data

DOI10.1016/J.JMVA.2012.08.004MaRDI QIDQ1931868zbMATH OpenOpenAlexFDO

Authors O. Friesen, Michael Stolz, M. Löwe

Publication date 16 January 2013

Published in Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1203.4387

zbMATH Keywords

cumulantsdependent random variablesMarčenko-Pastur lawrandom matrix theorysample covariance matrices

Mathematics Subject Classification ID

Limit theorems for vector-valued random variables (infinite-dimensional case) (60B12) Random matrices (probabilistic aspects) (60B20) Central limit and other weak theorems (60F05) Asymptotic properties of nonparametric inference (62G20) Estimation in multivariate analysis (62H12)

Abstract: It is known (Hofmann-Credner and Stolz (2008)) that the convergence of the mean empirical spectral distribution of a sample covariance matrix W_n = 1/n Y_n Y_n^t to the Marv{c}enko-Pastur law remains unaffected if the rows and columns of Y_n exhibit some dependence, where only the growth of the number of dependent entries, but not the joint distribution of dependent entries needs to be controlled. In this paper we show that the well-known CLT for traces of powers of W_n also extends to the dependent case.

Review text

The authors derive the central limit theorem for the traces of powers of the large-dimensional sample covariance matrix when the entries of the data matrix are assumed to be dependent without specifying the dependence structure. The result holds under the assumption that the number of dependent entries for each element of the data matrix does not grow too fast as the sample size grows up. Several important results about cumulants are presented as well.

Recommendations

• Gaussian fluctuations in complex sample covariance matrices
• Gaussian fluctuations for linear spectral statistics of large random covariance matrices
• Large sample covariance matrices of Gaussian observations with uniform correlation decay
• Gaussian Fluctuations for Random Matrices with Correlated Entries
• Gaussian fluctuation for Gaussian Wishart matrices of overall correlation
• Fluctuations for differences of linear eigenvalue statistics for sample covariance matrices
• Fluctuations for matrix-valued Gaussian processes
• Covariance Matrix Estimation From Linearly-Correlated Gaussian Samples
• Fluctuations of matrix entries of regular functions of sample covariance random matrices
• Estimation of deviation for random covariance matrices

Cited in

(10)

• Sample covariance matrix for random vectors with heavy tails
• Optimal shrinkage estimator for high-dimensional mean vector
• Fluctuations for matrix-valued Gaussian processes
• Direct shrinkage estimation of large dimensional precision matrix
• Gaussian fluctuations for linear spectral statistics of large random covariance matrices
• Fluctuations of Wigner-type random matrices associated with symmetric spaces of class DIII and CI
• Joint central limit theorem for eigenvalue statistics from several dependent large dimensional sample covariance matrices with application
• Marchenko–Pastur law with relaxed independence conditions
• Optimal Shrinkage-Based Portfolio Selection in High Dimensions
• Estimation of the global minimum variance portfolio in high dimensions

This page was built for publication: Gaussian fluctuations for sample covariance matrices with dependent data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1931868)