Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Statistical Analysis of Transfer Function Models with Conditional Heteroscedasticity

  • Baek, J.S. (Statistical Research Center for Complex System, Seoul National University) ;
  • Sohn, K.T. (Department of Statistics, Pusan National University) ;
  • Hwang, S.Y. (Department of Statistics, Sookmyung Women′s University)
  • Published : 2002.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This article introduces transfer function model (TFM) with conditional heteroscedasticity where ARCH concept is built into the traditional TFM of Box and Jenkins (1976). Model building strategies such as identification, estimation and diagnostics of the model are discussed and are illustrated via empirical study including simulated data and real data as well. Comparisons with the classical TFM are also made.

Keywords

References

  1. Statistics & Probability Letters v.31 The geometric ergodicity and existence of moments for a class of non-linear time series model An, H. Z.;Chen, M.;Huang, F. C.
  2. Proceeding of American Mathematical Society v.12 The Lindeberg-Levy theorem for martingale Billingsley, P.
  3. Time Series Analysis : Forecasting and Control, 2nd ed. Box, G. E. P.;Jenkins, J. M.
  4. Econometrica v.50 Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation Engle, R. F.
  5. Modeling Nonlinear Economic Relationships Granger, C. W. J.;Teraasvirta, T.
  6. Journal of Time Series Analysis v.15 On the squared residual autocorrelation in non-linear time series with conditional heteroscedasticity Li, W. K.;Mak, T. K.
  7. Time Series Analysis : Univariate and Multivariate Methods Wei, W. W. S.
  8. Journal of Time Series Analysis v.5 ARMA models with ARCH erros Weiss, A. A.