On the Bias in Estimates of Forecast Mean Squared Error

Abstract We examine the forecasting problem for a finite series of observations from either a nonseasonal or a seasonal autoregressive-moving average process. Four sources of bias in the usual estimator of forecast mean squared error are identified and analyzed for particular models using maximum likelihood and least squares parameter estimates. The usual estimator is found to be biased downwards, especially near the boundary of a stationary or invertible region, and the bias is severe for least squares estimators. An alternative estimator is proposed for the maximum likelihood case, which is shown generally to have reduced bias.

[1]  M. E. Muller,et al.  A Note on the Generation of Random Normal Deviates , 1958 .

[2]  George Marsaglia.  IMPROVING THE POLAR METHOD FOR GENERATING A PAIR OF NORMAL RANDOM VARIABLES , 1962 .

[3]  P. Whittle,et al.  Prediction and Regulation. , 1965 .

[4]  J. H. Wilkinson,et al.  Symmetric decomposition of a positive definite matrix , 1965 .

[5]  James Hardy Wilkinson,et al.  Symmetric decomposition of positive definite band matrices , 1965 .

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

[7]  Peter Bloomfield,et al.  On the error of prediction of a time series , 1972 .

[8]  Peter W Lewis,et al.  Naval Postgraduate School Random Number Generator Package LLRANDOM , 1973 .

[9]  G. Chow,et al.  MULTIPERIOD PREDICTIONS FROM STOCHASTIC DIFFERENCE EQUATIONS BY BAYESIAN METHODS , 1973 .

[10]  P. Lewis,et al.  Statistical Tests of Some Widely Used and Recently Proposed Uniform Random Number Generators , 1973 .

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

[12]  Ian McLeod.  Derivation of the Theoretical Autocovariance Function of Autoregressive–Moving Average Time Series , 1975 .

[13]  Taku Yamamoto,et al.  Asymptotic mean square prediction error for an autoregressive model with estimated coefficients , 1976 .

[14]  C. Ansley.  An algorithm for the exact likelihood of a mixed autoregressive-moving average process , 1979 .

[15]  Paul Newbold,et al.  Finite sample properties of estimators for autoregressive moving average models , 1980 .

[16]  C. Ansley.  Asymptotic distribution of residual autocorrelations from estimation of ARMA processes by Gram-Schmidt orthogonalization , 1981 .