A Study on the Effect of Box-Cox Power Transformation in AR(1) Model

  • Jin Hee (Graduate Department of Statistics, Hahkuk University of Foreign Studies) ;
  • I, Key-I (Associate Professor, Hahkuk University of Foreign Studies)
  • 발행 : 2000.04.01

초록

In time series analysis we generally use Box-Cox power transformation for variance stabilization. In this paper we show that order estimator and one step ahead forecast of transformed AR(1) model are approximately invariant to those of the original model under some assumptions. A small Monte-Carlo simulation is performed to support the results.

키워드

참고문헌

  1. Statistical Pattern Recognition(Second Edition) Fukunaga, K.
  2. Applied Linear Statistical Models(third Edition) Neter, J.;Wasserman, W.;Kutner, M.H.
  3. SAS/ETS User's Guide, Version 6(Second Edition) SAS
  4. Time Series Analysis. Univariate and Multivariate Merhod Wei, W.W.S.
  5. 시계열 분석 김원경
  6. 시계열분석 조신섭;손영숙
  7. 시계열 분석 조신섭;손영숙