臺灣博碩士論文加值系統

本文中討論了近單根模型之預測誤差的漸進性質,我們也發現在某些條件下,最小平方估計量會有較小的預測誤差.

The asymptotic expression for the mean-squared prediction error is discussed for the near-unit-root models. We find the mean-squared prediction error based on the ordinary least square estimator is smaller than the one using pretest estimating under some certain conditions.

Abstract
1 Introduction
2 Asymptotic Properties of the MSPE
3 Comparison of MSPE between OLS and Pretest Predictors
4 Conclusion
5 Appendix
Bibliography

[Chan & Wei (1987)] Chan, N.H. and Wei, C.Z. (1987), Asymptotic inference for nearly nonstationary AR(1) processes, Ann. of Statist. 15, 1050-1063.
[Dickey & Fuller (1979)] Dickey, D.A. and Fuller, W.A. (1979), Distribution of the estimators for autoregressive time series with a unit root, J. Am. Statist. Assoc. 74, 427-431.
[Dickey & Fuller (1981)] Dickey, D.A. and Fuller, W.A. (1981), Likelihood ratio statistics for autoregressive time series with a unit root, Econometrica 49, 1057-1072.
[Diebold & Kilian (2000)] Diebold, F.X. and Kilian, L. (2000), Unit-root tests are useful for selecting forecasting models, J. Bus. Econ. Statist. 18, 265-273.
[Fuller (1976)] Fuller, W.A. (1976), Introduction to Statistical Time Series, New York: Wiley.
[Ing (2000)] Ing, C.K. (2000), A note on mean-squared prediction errors of the least squares predictors in random walk models, J. Time Series Anal., forthcoming.
[Lai & Wei (1983)] Lai, T.Z. and Wei, C.Z. (1983), Asymptotic properties of general autoregressive models and strong consistency of least-squares estimates, J. Multivariate Anal. 13, 1-23.
[Phillips (1987a)] Phillips, P.C.B. (1987a), Times series regression with a unit root, Econometrica 55, 277-302.
[Phillips (1987b)] Phillips, P.C.B. (1987b), Towards a unified asymptotic theory of autoregression, Biometrika 74, 535-547.
[Phillips (1988)] Phillips, P.C.B. (1988), Regression theory for near-integrated time series, Econometrica 56, 1021-1043.
[Wei (1987)] Wei, C.Z. (1987), Adaptive prediction by the least squares predictors in stochastic regression models with application to time series, Ann. Statist. 15, 1667-1682.