The intersection of past and future for multivariate stationary processes

2015/01/04 by Akihiko Inoue, Inoue, Akihiko, Yukio Kasahara +3
Chemistry · Mathematics · #60G25 #Advanced Statistical Methods and Models #FOS: Mathematics #Primary 60G10 #Probability (math.PR) #Spectroscopy and Chemometric Analyses #Statistical and numerical algorithms #Statistics Theory (math.ST) #math.PR #math.ST #msc:60G10 #msc:60G25 #msc:62M10 #secondary 62M10 #stat.TH

paper · pdf · doi:10.48550/arxiv.1501.00625

8 pages

openalex publication_date 2015/01/04 · arxiv created 2015/05/23 · arxiv updated 2015/05/26 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

Abstract

We consider an intersection of past and future property of multivariate stationary processes which is the key to deriving various representation theorems for their linear predictor coefficient matrices. We extend useful spectral characterizations for this property from univariate processes to multivariate processes.

Related

• Baxter's inequality for finite predictor coefficients of multivariate long-memory stationary processes
• Modeling and estimation of multivariate discrete and continuous time\n stationary processes
• Prediction theory in continuous time
• Locally Stationary Processes
• Completely regular multivariate stationary process and the Muckenhoupt condition