Chapter 6 Forecasting with VARMA Models

Abstract Vector autoregressive moving-average (VARMA) processes are suitable models for producing linear forecasts of sets of time series variables. They provide parsimonious representations of linear data generation processes. The setup for these processes in the presence of stationary and cointegrated variables is considered. Moreover, unique or identified parameterizations based on the echelon form are presented. Model specification, estimation, model checking and forecasting are discussed. Special attention is paid to forecasting issues related to contemporaneously and temporally aggregated VARMA processes. Predictors for aggregated variables based alternatively on past information in the aggregated variables or on disaggregated information are compared.

[1]  Donald Poskitt,et al.  Identification of Echelon Canonical Forms for Vector Linear Processes Using Least Squares , 1992 .

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

[3]  Massimiliano Marcellino,et al.  Some Consequences of Temporal Aggregation in Empirical Analysis , 1999 .

[4]  Jan R. Magnus,et al.  The exact multi-period mean-square forecast error for the first-order autoregressive model , 1988 .

[5]  Bovas Abraham,et al.  Temporal Aggregation and Time Series , 1982 .

[6]  Frank Schorfheide,et al.  VAR forecasting under misspecification , 2005 .

[7]  H. Akaike.  Stochastic theory of minimal realization , 1974 .

[8]  Helmut Lütkepohl,et al.  Order Selection in Testing for the Cointegrating Rank of a VAR Process , 1997 .

[9]  David F. Hendry,et al.  Forecasting Aggregates by Disaggregates , 2005 .

[10]  Gordon C.R. Kemp.  The Behavior Of Forecast Errors From A Nearly Integrated Ar(1) Model As Both Sample Size And Forecast Horizon Become Large , 1999 .

[11]  E. Hannan,et al.  The statistical theory of linear systems , 1989 .

[12]  Helmut Lütkepohl.  The joint asymptotic distribution of multistep prediction errors of estimated vector autoregressions , 1985 .

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

[14]  C. Granger,et al.  Experience with Forecasting Univariate Time Series and the Combination of Forecasts , 1974 .

[15]  Dietmar Bauer,et al.  A Canonical Form for Unit Root Processes in the State Space Framework , 2002 .

[16]  Gregory C. Reinsel,et al.  VECTOR AUTOREGRESSIVE MODELS WITH UNIT ROOTS AND REDUCED RANK STRUCTURE:ESTIMATION. LIKELIHOOD RATIO TEST, AND FORECASTING , 1992 .

[17]  J. Stock,et al.  A Comparison of Linear and Nonlinear Univariate Models for Forecasting Macroeconomic Time Series , 1998 .

[18]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[19]  P. R. Krishnaiah,et al.  Developments in Statistics , 1979 .

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

[21]  K. Wallis.  Multiple Time Series Analysis and the Final Form of Econometric Models , 1977 .

[22]  Michael P. Clements,et al.  FORECASTING ECONOMIC TIME SERIES , 2000, Econometric Theory.

[23]  Helmut Lütkepohl,et al.  Analysis of cointegrated VARMA processes , 1997 .

[24]  Michael P. Clements,et al.  Forecasting Non-Stationary Economic Time Series , 1999 .

[25]  Helmut Lütkepohl.  Forecasting Cointegrated VARMA Processes , 1999 .

[26]  Helmut Lütkepohl,et al.  Consistent Specification of Cointegrated Autoregressive Moving-Average Systems , 1995 .

[27]  Søren Johansen,et al.  Likelihood Analysis of the I(2) Model , 1997 .

[28]  Paul Newbold,et al.  Asymptotic mean‐squared forecast error when an autoregression with linear trend is fitted to data generated by an I(0) or I(1) process , 2004 .

[29]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

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

[31]  A. Timmermann,et al.  Small Sample Properties of Forecasts from Autoregressive Models Under Structural Breaks , 2003, SSRN Electronic Journal.

[32]  Irwin Guttman,et al.  Forecasting contemporal aggregates of multiple time series , 1980 .

[33]  Jean-Marie Dufour,et al.  Unbiasedness of Predictions from Etimated Vector Autoregressions , 1985, Econometric Theory.

[34]  Aman Ullah,et al.  Finite Sample Econometrics , 2004 .

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

[36]  Helmut Lütkepohl,et al.  Infinite Order Cointegrated Vector Autoregressive Processes:Estimation and Inference , 1994 .

[37]  Masanao Aoki,et al.  State Space Modeling of Time Series , 1987 .

[38]  E. Hannan.  The Identification and Parameterization of ARMAX and State Space Forms , 1976 .

[39]  Timo Teräsvirta,et al.  Chapter 8 Forecasting economic variables with nonlinear models , 2006 .

[40]  Robert F. Engle,et al.  Forecasting and testing in co-integrated systems , 1987 .

[41]  S. G. Koreisha,et al.  Identification of Nonzero Elements in the Polynomial Matrices of Mixed Varma Processes , 1987 .

[42]  William W. S. Wei,et al.  Time series analysis - univariate and multivariate methods , 1989 .

[43]  Søren Johansen,et al.  A Stastistical Analysis of Cointegration for I(2) Variables , 1995, Econometric Theory.

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

[45]  Gregory C. Reinsel,et al.  Prediction mean square error for non-stationary multivariate time series using estimated parameters , 1987 .

[46]  C. Sims.  MACROECONOMICS AND REALITY , 1977 .

[47]  Helmut Lütkepohl,et al.  Linear transformations of vector ARMA processes , 1984 .

[48]  Michael P. Clements,et al.  A companion to economic forecasting , 2004 .

[49]  Jae H. Kim.  Asymptotic and bootstrap prediction regions for vector autoregression , 1999 .

[50]  C. Granger.  Some properties of time series data and their use in econometric model specification , 1981 .

[51]  Gregory C. Reinsel,et al.  Estimation and Testing for Unit Roots in a Partially Nonstationary Vector Autoregressive Moving Average Model , 1995 .

[52]  R. Bhansali.  Linear Prediction by Autoregressive Model Fitting in the Time Domain , 1978 .

[53]  Richard T. Baillie,et al.  Prediction from the Dynamic Simultaneous Equation Model with Vector Autoregressive Errors , 1981 .

[54]  Timo Teräsvirta,et al.  Forecasting economic variables with nonlinear models , 2005 .

[55]  Robert Kohn,et al.  When is an aggregate of a time series efficiently forecast by its past , 1982 .

[56]  Bart De Moor,et al.  N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems , 1994, Autom..

[57]  H. Lütkepohl.  COMPARISON OF CRITERIA FOR ESTIMATING THE ORDER OF A VECTOR AUTOREGRESSIVE PROCESS , 1985 .

[58]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[59]  Matteo Grigoletto,et al.  Bootstrap prediction intervals for autoregressions: some alternatives , 1998 .

[60]  Gregory C. Reinsel,et al.  Estimation for Partially Nonstationary Multivariate Autoregressive Models , 1990 .

[61]  Helmut Luetkepohl,et al.  Estimating the Kronecker Indices of Cointegrated Echelon�?Form Varma Models , 1998 .

[62]  John Geweke,et al.  A Comparison of Autoregressive Univariate Forecasting Procedures for Macroeconomic Time Series , 1984 .

[63]  Guy Laroque,et al.  Polynomial cointegration estimation and test , 1994 .

[64]  E. J. Hannan,et al.  Estimating the dimension of a linear system , 1981 .

[65]  N. Haldrup.  An Econometric Analysis of I(2) Variables , 1998 .

[66]  D. Stram,et al.  TEMPORAL AGGREGATION IN THE ARIMA PROCESS , 1986 .

[67]  George Kapetanios,et al.  A Note on an Iterative Least Squares Estimation Method for Arma and Varma Models , 2002 .

[68]  M. Wagner,et al.  Estimating cointegrated systems using subspace algorithms , 2002 .

[69]  Ruey S. Tsay,et al.  Parsimonious Parameterization of Vector Autoregressive Moving Average Models , 1989 .

[70]  H. White,et al.  Cointegration, causality, and forecasting : a festschrift in honour of Clive W.J. Granger , 1999 .

[71]  C. Granger,et al.  Forecasting Economic Time Series. , 1988 .

[72]  Helmut Lütkepohl,et al.  Specification of Echelon-Form VARMA Models , 1996 .

[73]  P. Maher,et al.  Handbook of Matrices , 1999, The Mathematical Gazette.

[74]  Donald Poskitt,et al.  On the specification of cointegrated autoregressive moving-average forecasting systems , 2003 .

[75]  K. Hubrich.  Forecasting Euro Area Inflation: Does Aggregating Forecasts by Hicp Component Improve Forecast Accuracy? , 2003 .

[76]  Ernst Schaumburg,et al.  Likelihood analysis of seasonal cointegration , 1999 .

[77]  E. J. Hannan,et al.  Vector linear time series models , 1976, Advances in Applied Probability.

[78]  Ruey S. Tsay,et al.  IDENTIFYING MULTIVARIATE TIME SERIES MODELS , 1989 .

[79]  Guido Masarotto,et al.  Bootstrap prediction intervals for autoregressions , 1990 .

[80]  Roch Roy,et al.  On the identification of ARMA echelon-form models* , 1992 .

[81]  A. A. Weiss.  Systematic sampling and temporal aggregation in time series models , 1984 .

[82]  Aritra Basu,et al.  On Asymptotic Prediction Problems for Multivariate Autoregressive Models in the Unstable Nonexplosive Case , 1987 .

[83]  Clive W. J. Granger,et al.  Prediction with a generalized cost of error function , 1969 .

[84]  Andrew Harvey,et al.  Chapter 7 Forecasting with Unobserved Components Time Series Models , 2006 .

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

[86]  Norman R. Swanson,et al.  Temporal aggregation and spurious instantaneous causality in multiple time series models , 2002 .

[87]  G. Reinsel.  Elements of Multivariate Time Series Analysis , 1995 .

[88]  H. Lütkepohl,et al.  Infinite-Order Cointegrated Vector Autoregressive Processes , 1996, Econometric Theory.

[89]  K. Brewer.  Some consequences of temporal aggregation and systematic sampling for ARMA and ARMAX models , 1973 .

[90]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[91]  Taku Yamamoto.  On the Treatment of Autocorrelated Errors in the Multiperiod Prediction of Dynamic Simultaneous Equation Models , 1980 .

[92]  Pentti Saikkonen,et al.  Estimation and Testing of Cointegrated Systems by an Autoregressive Approximation , 1992, Econometric Theory.

[93]  C. Granger.  Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

[94]  Maurice Henry Quenouille,et al.  The analysis of multiple time-series , 1957 .

[95]  William W. S. Wei,et al.  Some Consequences of Temporal Aggregation in Seasonal Time Series Models , 1979 .

[96]  Helmut Lütkepohl,et al.  Forecasting temporally aggregated vector ARMA processes , 1986 .

[97]  Jean-Marie Dufour,et al.  Unbiasedness of Predictions From Estimated Vector Autoregressions , 1983 .

[98]  Andrew Harvey,et al.  Forecasting with Unobserved Components Time Series Models , 2006 .

[99]  R. J. Bhansali,et al.  Multi‐Step Forecasting , 2007 .

[100]  G. C. Tiao,et al.  Model Specification in Multivariate Time Series , 1989 .

[101]  Arnold Zellner,et al.  Seasonal Analysis of Economic Time Series , 1981 .

[102]  L. Telser,et al.  Discrete Samples and Moving Sums in Stationary Stochastic Processes , 1967 .

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

[104]  E. J. Hannan,et al.  Multiple time series , 1970 .

[105]  Michael Sampson,et al.  The Effect of Parameter Uncertainty on Forecast Variances and Confidence Intervals for Unit Root and Trend Stationary Time-Series Models , 1991 .

[106]  ON LINEAR PROCESSES WITH GIVEN MOMENTS , 1987 .

[107]  G. C. Tiao,et al.  Asymptotic behaviour of temporal aggregates of time series , 1972 .

[108]  Juan Romo,et al.  Bootstrap predictive inference for ARIMA processes , 2004 .

[109]  J. Stock,et al.  Macroeconomic forecasting in the Euro area: Country specific versus area-wide information , 2003 .

[110]  Helmut Lütkepohl,et al.  Forecasting Vector ARMA Processes with Systematically Missing Observations , 1986 .

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

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

[113]  C. Granger,et al.  Handbook of Economic Forecasting , 2006 .

[114]  S. Gregoir,et al.  MULTIVARIATE TIME SERIES WITH VARIOUS HIDDEN UNIT ROOTS, PART II , 1999, Econometric Theory.

[115]  S. Gregoir,et al.  MULTIVARIATE TIME SERIES WITH VARIOUS HIDDEN UNIT ROOTS, PART I , 1999, Econometric Theory.

[116]  G. Reinsel,et al.  Prediction of multivariate time series by autoregressive model fitting , 1985 .

[117]  Helmut Ltkepohl,et al.  New Introduction to Multiple Time Series Analysis , 2007 .

[118]  Takeshi Amemiya,et al.  The Effect of Aggregation on Prediction in the Autoregressive Model , 1972 .

[119]  Helmut Lütkepohl,et al.  Forecasting aggregated vector ARMA processes , 1987 .

[120]  S. Johansen.  Likelihood-Based Inference in Cointegrated Vector Autoregressive Models , 1996 .

[121]  Helmut Lütkepohl,et al.  A REVIEW OF SYSTEMS COINTEGRATION TESTS , 2001 .

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

[123]  Paul Kabaila,et al.  ON BOOTSTRAP PREDICTIVE INFERENCE FOR AUTOREGRESSIVE PROCESSES , 1993 .