Maximum Likelihood Fitting of ARMA Models to Time Series With Missing Observations

The method of calculating the exact likelihood function of a stationary autoregressive moving average (ARMA) time series based on Akaike's Markovian representation and using Kalman recursive estimation is reviewed. This state space approach involves matrices and vectors with dimensions equal to Max (p, q + 1) where p is the order of the autoregression and q is the order of the moving average, rather than matrices with dimensions equal to the number of observations. A key to the calculation of the exact likelihood function is the proper calculation of the initial state covariance matrix. The inclusion of observational error into the model is discussed as is the extension to missing observations. The use of a nonlinear optimization program gives the maximum likelihood estimates of the parameters and allows for model identification based on Akaike's Information Criterion (AIC). An example is presented fitting models to western United States drought data.

[1]  Richard H. Jones.  FITTING A CONTINUOUS TIME AUTOREGRESSION TO DISCRETE DATA , 1981 .

[2]  Richard H. Jones,et al.  Identification and autoregressive spectrum estimation , 1974, CDC 1974.

[3]  Peter E. Caines,et al.  Maximum likelihood estimation of parameters in multivariate Gaussian stochastic processes (Corresp.) , 1974, IEEE Trans. Inf. Theory.

[4]  Andrew Harvey,et al.  Maximum likelihood estimation of regression models with autoregressive-moving average disturbances , 1979 .

[5]  T. Kailath.  The innovations approach to detection and estimation theory , 1970 .

[6]  James Durbin,et al.  The fitting of time series models , 1960 .

[7]  N. Levinson.  The Wiener (Root Mean Square) Error Criterion in Filter Design and Prediction , 1946 .

[8]  R. Galbraith,et al.  ON THE INVERSES OF SOME PATTERNED MATRICES ARISING IN THE THEORY OF STATIONARY TIME SERIES , 1974 .

[9]  H. Akaike.  Maximum likelihood identification of Gaussian autoregressive moving average models , 1973 .

[10]  H. Akaike.  Covariance Matrix Computation of the State Variable of a Stationary Gaussian Process , 1978 .

[11]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[12]  P. Newbold.  The exact likelihood function for a mixed autoregressive-moving average process , 1974 .

[13]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[14]  H. Akaike.  Markovian Representation of Stochastic Processes by Canonical Variables , 1975 .

[15]  Muketar M. Ali.  Analysis of autoregressive-moving average models: Estimation and prediction , 1977 .

[16]  H. Akaike.  Markovian Representation of Stochastic Processes and Its Application to the Analysis of Autoregressive Moving Average Processes , 1974 .