DETERMINING THE ORDER OF A VECTOR AUTOREGRESSION WHEN THE NUMBER OF COMPONENT SERIES IS LARGE
- 1 January 1993
- journal article
- Published by Wiley in Journal of Time Series Analysis
- Vol. 14 (1) , 47-69
- https://doi.org/10.1111/j.1467-9892.1993.tb00129.x
Abstract
We contrast the performance of several methods used for identifying the order of vector autoregressive (VAR) processes when the numberKof component series is large. Through simulation experiments we show that their performance is dependent onK, the number of nonzero elements in the polynomial matrices of the VAR parameters and the permitted upper limit of the order used in testing the autoregressive structure. In addition we introduce a new quite powerful multivariate order determination criterion.Keywords
This publication has 20 references indexed in Scilit:
- An improved estimation method for univariate autoregressive modelsJournal of Multivariate Analysis, 1988
- On the use of autoregressive order determination criteria in multivariate white noise testsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Estimation of the Polynomial Matrices of Vector Moving Average ProcessesJournal of Statistical Computation and Simulation, 1987
- Forecasting Wheat Exports: Do Exchange Rates Matter?Journal of Business & Economic Statistics, 1987
- Loss of spectral peaks in autoregressive spectral estimationBiometrika, 1987
- A forecasting comparison of some var techniquesInternational Journal of Forecasting, 1986
- Autoregressive modelling and money-income causality detectionJournal of Monetary Economics, 1981
- Autoregressive Modeling of Canadian Money and Income DataJournal of the American Statistical Association, 1979
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- A Note on the Generation of Random Normal DeviatesThe Annals of Mathematical Statistics, 1958