IDENTIFYING MULTIVARIATE TIME SERIES MODELS
Journal of Time Series AnalysisPublished 1 July 1989
Ruey S. Tsay
Citations35
SJR quartileQ1
SJR score0.94
SNIP1.27
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
Abstract. This paper is concerned with how canonical variate analysis can be used to identify the structure of a linear multivariate time series model. The procedure used is based on that of Akaike and Cooper and Wood. A correction and a refinement are made, however. The correction is on the testing statistic and the refinement on the allowed order ( p, q ). Appropriate asymptotic distributions for testing zero canonical correlations are also given.
Keywords
MathematicsDecision SciencesEconomics, Econometrics and Finance
IEEE Transactions on Automatic ControlA new look at the statistical model identification
50,732 Citations1974Hirotugu Akaike
Journal of the Royal Statistical Society Series A (General)Theory and Application of the Linear Model.
1,176 Citations1977J. A. Nelder, Franklin A. Graybill
This book integrates the linear statistical model within the context of analysis of variance, correlation and regression, and design of experiments and is a time tested, authoritative resource for experimenters, statistical consultants, and students.
Mathematics in Science and Engineering/Mathematics in science and engineeringCanonical Correlation Analysis of Time Series and the Use of an Information Criterion
664 Citations1976Hirotugu Akaike
The Annals of StatisticsLimiting Distributions of Least Squares Estimates of Unstable Autoregressive Processes
637 Citations1988Ngai Hang Chan, Ching-Zong Wei
Journal of the Royal Statistical Society Series B (Statistical Methodology)Model Specification in Multivariate Time Series
360 Citations1989George C. Tiao, Ruey S. Tsay
The concept of scalar component models within the vector ARMA framework is introduced to reveal possibly hidden simplifying structures of the process, to achieve parsimony in parameterization and to identify the exchangeable models.
SIAM Journal on ControlMarkovian Representation of Stochastic Processes by Canonical Variables
356 Citations1975Hirotugu Akaike
The structure of the information interface between the future and the past of a discrete-time stochastic process is analyzed by using the concepts of canonical correlation analysis and two extreme Markovian representations are obtained.
BiometrikaReduced rank models for multiple time series
173 Citations1986Raja P. Velu, Gregory C. Reinsel +1 more
Journal of Multivariate AnalysisAsymptotic properties of general autoregressive models and strong consistency of least-squares estimates of their parameters
162 Citations1983Tze Leung Lai, Ching-Zong Wei
BiometrikaUse of canonical analysis in time series model identification
116 Citations1985Ruey S. Tsay, George C. Tiao
The Annals of StatisticsConsistency Properties of Least Squares Estimates of Autoregressive Parameters in ARMA Models
113 Citations1983George C. Tiao, Ruey S. Tsay
BiometrikaSome results on multivariate autoregressive index models
87 Citations1983Gregory C. Reinsel
Journal of Time Series AnalysisIDENTIFYING MULTIVARIATE TIME SERIES MODELS
48 Citations1982David M. L. Cooper, Eric F. Wood
Communication in Statistics- Theory and MethodsSample moments of the autocorrelations of moving average processes and a modification to bartlett'sasymptotic variance formula
8 Citations1980Neville Davies, Paul Newbold
It is shown that Bartlett's asymptotic formula for the variance of the sample autocorrelations of moving average processes is a large overestimate when considering finitesample sizes.