Multi-step estimation and forecasting in dynamic models

Abstract We consider the situation in which a researcher uses a misspecified model for forecasting. If the interest is in multi-step forecasting and the accuracy of the forecasts is measured through the sum of squared multi-step forecast errors, then in large samples it is preferable to minimize corresponding sum of squared in-sample multi-step forecast errors. We derive the asymptotic properties of the resulting estimator. To asses the behavior of the estimator in small samples, we perform a Monte Carlo experiment. In most of the cases considered, OLS outperforms the estimator. We conjecture that this occurs because the estimator is still defined on the basis of squared errors.

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

[2]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[3]  D. Andrews.  CONSISTENCY IN NONLINEAR ECONOMETRIC MODELS: A GENERIC UNIFORM LAW OF LARGE NUMBERS , 1987 .

[4]  H. White.  Asymptotic theory for econometricians , 1985 .

[5]  A. A. Weiss,et al.  Estimating Time Series Models using the Relevant Forecast Evaluation Criterion , 1984 .

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

[7]  Jean-Marie Dufour.  Unbiasedness of Predictions from Estimated Autoregressions When the True Order Is Unknown , 1984 .

[8]  Peter C. B. Phillips,et al.  The sampling distribution of forecasts from a first-order autoregression , 1979 .

[9]  Lawrence R. Klein,et al.  Estimation and Prediction in Dynamic Econometric Models , 1974 .

[10]  H. White,et al.  Nonlinear Regression with Dependent Observations , 1984 .

[11]  R. Jennrich.  Asymptotic Properties of Non-Linear Least Squares Estimators , 1969 .

[12]  H. White,et al.  Misspecified models with dependent observations , 1982 .

[13]  A. Gallant,et al.  Nonlinear Statistical Models , 1988 .

[14]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[15]  J. Hausman.  Specification tests in econometrics , 1978 .

[16]  H N Johnston.  A Note on the Estimation and Prediction Inefficiency of "Dynamic" Estimators , 1974 .

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

[18]  Ian Domowitz.  New Directions in Non-linear Estimation with Dependent Observations , 1985 .

[19]  H. White,et al.  NONLINEAR REGRESSION ON CROSS-SECTION DATA , 1980 .

[20]  Lawrence R. Klein,et al.  An Essay On The Theory Of Economic Prediction , 1971 .