Open Access
2015 Discussion of “High-dimensional autocovariance matrices and optimal linear prediction”
Rob J. Hyndman
Electron. J. Statist. 9(1): 792-796 (2015). DOI: 10.1214/14-EJS953

Abstract

I propose new ACF and PACF plots based on the autocovariance estimators of McMurry and Politis. I also show that the forecasting methods they propose perform poorly compared to some relatively simple autoregression algorithms already available.

Citation

Download Citation

Rob J. Hyndman. "Discussion of “High-dimensional autocovariance matrices and optimal linear prediction”." Electron. J. Statist. 9 (1) 792 - 796, 2015. https://doi.org/10.1214/14-EJS953

Information

Received: 1 October 2014; Published: 2015
First available in Project Euclid: 3 November 2014

zbMATH: 1309.62153
MathSciNet: MR3331858
Digital Object Identifier: 10.1214/14-EJS953

Keywords: Autocorrelation , Autoregression , data visualization , forecasting , serial correlation , time series graphics

Rights: Copyright © 2015 The Institute of Mathematical Statistics and the Bernoulli Society

Vol.9 • No. 1 • 2015
Back to Top