Estimation of Autocovariance Matrices for Infinite Dimensional Vector Linear Process

20 Pages Posted: 16 Apr 2014

See all articles by Monika Bhattacharjee

Monika Bhattacharjee

Indian Statistical Institute, Kolkata - Statistics and Mathematics Unit

Arup Bose

Indian Statistical Institute, Kolkata - Statistics and Mathematics Unit

Date Written: May 2014

Abstract

Consider an infinite dimensional vector linear process. Under suitable assumptions on the parameter space, we provide consistent estimators of the autocovariance matrices. In particular, under causality, this includes the infinite‐dimensional vector autoregressive (IVAR) process. In that case, we obtain consistent estimators for the parameter matrices. An explicit expression for the estimators is obtained for IVAR(1), under a fairly realistic parameter space. We also show that under some mild restrictions, the consistent estimator of the marginal large dimensional variance–covariance matrix has the same convergence rate as that in case of i.i.d. samples.

Keywords: High‐dimensional data, IVAR, spatial variable, cross‐sectional variables, variance–covariance matrix, marginal variance–covariance matrix, coefficient matrix, parameter matrix, k‐th order autocovariance matrix, banding, consistency, convergence rate, operator norm

Suggested Citation

Bhattacharjee, Monika and Bose, Arup, Estimation of Autocovariance Matrices for Infinite Dimensional Vector Linear Process (May 2014). Journal of Time Series Analysis, Vol. 35, Issue 3, pp. 262-281, 2014, Available at SSRN: https://ssrn.com/abstract=2425407 or http://dx.doi.org/10.1111/jtsa.12063

Monika Bhattacharjee (Contact Author)

Indian Statistical Institute, Kolkata - Statistics and Mathematics Unit

India

Arup Bose

Indian Statistical Institute, Kolkata - Statistics and Mathematics Unit ( email )

India

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
3
Abstract Views
393
PlumX Metrics