scholarly journals High-Dimensional Vector Autoregressive Time Series Modeling via Tensor Decomposition

2019 ◽  
Author(s):  
Di Wang ◽  
Heng Lian ◽  
Yao Zheng ◽  
Guodong Li
Keyword(s):  
Time Series ◽  
Tensor Decomposition ◽  
High Dimensional ◽  
Dimensional Vector ◽  
Time Series Modeling ◽  
Autoregressive Time Series ◽  
Vector Autoregressive

scholarly journals Justification of Wold’s Theorem and the Unbiasedness of a Stable Vector Autoregressive Time Series Model Forecasts

2017 ◽  
Vol 6 (2) ◽  
pp. 1
Author(s):  
Iberedem A. Iwok
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Autoregressive Process ◽  
Time Series Model ◽  
Average Process ◽  
Moving Average Process ◽  
Autoregressive Time Series ◽  
Vector Autoregressive ◽  
Vector Autoregressive Process ◽  
Vector Time Series

In this work, the multivariate analogue to the univariate Wold’s theorem for a purely non-deterministic stable vector time series process was presented and justified using the method of undetermined coefficients. By this method, a finite vector autoregressive process of order  [] was represented as an infinite vector moving average () process which was found to be the same as the Wold’s representation. Thus, obtaining the properties of a  process is equivalent to obtaining the properties of an infinite  process. The proof of the unbiasedness of forecasts followed immediately based on the fact that a stable VAR process can be represented as an infinite VEMA process.

scholarly journals Online Topology Identification From Vector Autoregressive Time Series

2021 ◽  
Vol 69 ◽  
pp. 210-225
Author(s):  
Bakht Zaman ◽  
Luis Miguel Lopez Ramos ◽  
Daniel Romero ◽  
Baltasar Beferull-Lozano
Keyword(s):  
Time Series ◽  
Autoregressive Time Series ◽  
Vector Autoregressive ◽  
Topology Identification

scholarly journals “Plug-in” Statistical Forecasting of Vector Autoregressive Time Series with Missing Values

2016 ◽  
Vol 34 (2) ◽  
Author(s):  
Yuriy Kharin ◽  
Aliaksandr Huryn
Keyword(s):  
Time Series ◽  
Maximum Likelihood ◽  
Numerical Experiments ◽  
Missing Values ◽  
Asymptotic Properties ◽  
Mean Square ◽  
Unknown Parameters ◽  
Autoregressive Time Series ◽  
Statistical Forecasting ◽  
Vector Autoregressive

The problems of statistical forecasting of vector autoregressive time series with missing values are considered. The maximum likelihood forecast is constructed and its mean square risk is evaluated for the case of known parameters. The “plug-in” forecast and statistical estimators are constructed for unknown parameters. Asymptotic properties of constructed estimators are analyzed. Results of numerical experiments are presented.

Sign in / Sign up

Export Citation Format

Share Document