Model Specification in Multivariate Time Series

SUMMARY We propose a method to specify an appropriate yet parsimonious vector autoregressive moving average (ARMA) model for a given multivariate time series. By considering con temporaneous linear transformations of the vector process, we introduce the concept of scalar component models within the vector ARMA framework (a) to reveal possibly hidden simplifying structures of the process, (b) to achieve parsimony in parameterization and (c) to identify the exchangeable models. The simplifyingstructures are of particular importance in the analysis of multivariate time series because they are often not obvious from the observed data but can be used to gain insights to the process under study. The analytical tool used to search for scalar component models is a canonical correlation analysis of vector processes and the proposed procedures are illustrated via two real examples.

[1]  Victor Solo,et al.  The exact likelihood for a multivariate ARMA model , 1984 .

[2]  P. Robinson,et al.  Generalized canonical analysis for time series , 1973 .

[3]  Nicholas P. Jewell,et al.  Canonical Correlations of Past and Future for Time Series: Bounds and Computation , 1983 .

[4]  M. Bartlett.  On the Theoretical Specification and Sampling Properties of Autocorrelated Time‐Series , 1946 .

[5]  Gwilym M. Jenkins,et al.  SOME ASPECTS OF MODELLING AND FORECASTING MULTIVARIATE TIME SERIES , 1981 .

[6]  G. C. Tiao,et al.  A canonical analysis of multiple time series , 1977 .

[7]  C. Z. Wei,et al.  Limiting Distributions of Least Squares Estimates of Unstable Autoregressive Processes , 1988 .

[8]  G. C. Tiao,et al.  Use of canonical analysis in time series model identification , 1985 .

[9]  G. Kedem,et al.  Computation of the exact likelihood function of multivariate moving average models , 1978 .

[10]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[11]  H. Akaike.  A new look at the statistical model identification , 1974 .

[12]  D. Findley.  ON SOME AMBIGUITIES ASSOCIATED WITH THE FITTING OF ARMA MODELS TO TIME SERIES , 1984 .

[13]  E. Parzen.  Multiple Time Series: Determining the Order of Approximating Autoregressive Schemes. , 1975 .

[14]  Gregory C. Reinsel,et al.  Nested Reduced-Rank Autoregressive Models for Multiple Time Series , 1988 .

[15]  Nicholas P. Jewell,et al.  Canonical Correlations of Past and Future for Time Series: Definitions and Theory , 1983 .

[16]  H. Akaike.  Canonical Correlation Analysis of Time Series and the Use of an Information Criterion , 1976 .

[17]  P. Robinson,et al.  Identification, estimation and large-sample theory for regressions containing unobservable variables , 1974 .

[18]  A. Zellner,et al.  Time series analysis and simultaneous equation econometric models , 1974 .

[19]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[20]  M. H. Quenouille,et al.  The analysis of multiple time-series , 1958 .

[21]  E. Hannan.  The identification of vector mixed autoregressive-moving average system , 1969 .

[22]  C. Granger,et al.  Co-integration and error correction: representation, estimation and testing , 1987 .

[23]  G. C. Tiao,et al.  Multiple Time Series Modeling and Extended Sample Cross-Correlations , 1983 .

[24]  P. Phillips,et al.  Multiple Time Series Regression with Integrated Processes , 1986 .

[25]  Victor Solo,et al.  Topics in advanced time series analysis , 1986 .

[26]  Steven C. Hillmer,et al.  Likelihood Function of Stationary Multiple Autoregressive Moving Average Models , 1979 .

[27]  S. Taylor.  Forecasting Economic Time Series , 1979 .

[28]  G. C. Tiao,et al.  Asymptotic properties of multivariate nonstationary processes with applications to autoregressions , 1990 .

[29]  G. Walton.  A note on nonrandomized Neyman-shortest unbiased confidence intervals for the binomial and Poisson parameters , 1970 .

[30]  G. T. Wilson.  The Estimation of Parameters in Multivariate Time Series Models , 1973 .

[31]  A. D. Hall,et al.  The exact likelihood function of multivariate autoregressive-moving average models , 1979 .

[32]  Gregory C. Reinsel,et al.  Reduced rank models for multiple time series , 1986 .

[33]  Kenneth F. Wallis,et al.  Multiple Time Series Modelling: Another Look at the Mink‐Muskrat Interaction , 1978 .

[34]  Eric F. Wood,et al.  IDENTIFYING MULTIVARIATE TIME SERIES MODELS , 1982 .

[35]  George E. P. Box,et al.  Identifying a Simplifying Structure in Time Series , 1987 .

[36]  Gregory C. Reinsel.  Some results on multivariate autoregressive index models , 1983 .

[37]  E. J. Hannan,et al.  Multivariate linear time series models , 1984, Advances in Applied Probability.

[38]  G. C. Tiao,et al.  Modeling Multiple Time Series with Applications , 1981 .