A Comparison of Robust Parameter Estimations for Autoregressive Models

자기회귀모형에서의 로버스트한 모수 추정방법들에 관한 연구

  • 강희정 (전북대학교 자연과학대학 수학.통계정보과학부, 기초과학연구소) ;
  • 김순영 (전북대학교 자연과학대학 전산통계학과)
  • Published : 2000.04.30

Abstract

In this paper, we study several parameter estimation methods used for autoregressive processes and compare them in view of forecasting. The least square estimation, least absolute deviation estimation, robust estimation are compared through Monte Carlo simulations.

References

  1. Robust Estimation and Testing Staudte, R. G.;Sheather, S. J.
  2. Biometrika v.69 The Cramer-Rao Bound and Robust M-estimates for Autoregressions Martin, R. D.
  3. Journal of the American Statistical Association v.81 Robust Estimates for ARMA Models Bustors, O. H.;Yohai, V. J.
  4. Time Series: Theory and Methods(2nd ed.) Brockwell, P. J.;Davis, R. A.
  5. Journal of the Korean Statistical Society v.27 Strong Representations for LAD Estimators in AR⑴ Models Kang, H. J.;Shin, K. I.
  6. Stochastic Processes and their Applications v.57 Bahadur-Kiefer Representations for GM-estimators in Autoregression Models Koul, H. L.;Zhu, Z.
  7. 응용통계연구 v.12 no.2 시계열모형에서 추정함수를 이용한 로버스트 추론방법 차경엽;김삼용;이성덕
  8. Least Absolute Deviations : Theory, Applications and Algorithms Bloomfield, P.;Steiger, W. L.
  9. Z. Wahrscheinlichkeitstheorie verw. Gebiete v.59 General M-estimates for Contaminated p-th Order Autoregressive Processes: Consistency and Asymptotic Normality Bustos, O. H.
  10. Journal of the American Statistical Association v.74 Robust Estimation of the First-Order Autoregressive Parameter Denby, L.;Martin, R. D.