Spectra of Empirical Auto-Covariance Matrices
arXiv:1112.4877 · doi:10.1209/0295-5075/99/20008
Abstract
We compute spectra of sample auto-covariance matrices of second order stationary stochastic processes. We look at a limit in which both the matrix dimension and the sample size used to define empirical averages diverge, with their ratio kept fixed. We find a remarkable scaling relation which expresses the spectral density of sample auto-covariance matrices for processes with dynamical correlations as a continuous superposition of appropriately rescaled copies of the spectral density for a sequence of uncorrelated random variables. The rescaling factors are given by the Fourier transform of the auto-covariance function of the stochastic process. We also obtain a closed-form approximation for the scaling function . This depends on the shape parameter , but is otherwise universal: it is independent of the details of the underlying random variables, provided only they have finite variance. Our results are corroborated by numerical simulations using auto-regressive processes.
arXiv comment4 pages, 2 figures
References in corpus (6)
- Noise Dressing of Financial Correlation Matrices
- Universal and non-universal properties of cross-correlations in financial time series
- On Orthogonal and Symplectic Matrix Ensembles
- Large Deviations of the Maximum Eigenvalue in Wishart Random Matrices
- Large Deviations of the Smallest Eigenvalue of the Wishart-Laguerre Ensemble
- On the Eigenvalue Density of Real and Complex Wishart Correlation Matrices