Stationary Gaussian Markov processes as limits of stationary autoregressive time series

Journal Article

© 2017 Elsevier Inc. We consider the class, Cp, of all zero mean stationary Gaussian processes, {Yt:t∈(−∞,∞)} with p derivatives, for which the vector valued process {(Yt(0),…,Yt(p)):t≥0} is a p+1-vector Markov process, where Yt(0)=Y(t). We provide a rigorous description and treatment of these stationary Gaussian processes as limits of stationary AR(p) time series.

Full Text

Duke Authors

Cited Authors

  • Ernst, PA; Brown, LD; Shepp, L; Wolpert, RL

Published Date

  • March 1, 2017

Published In

Volume / Issue

  • 155 /

Start / End Page

  • 180 - 186

Electronic International Standard Serial Number (EISSN)

  • 1095-7243

International Standard Serial Number (ISSN)

  • 0047-259X

Digital Object Identifier (DOI)

  • 10.1016/j.jmva.2016.12.008

Citation Source

  • Scopus