Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Outlier Detection Diagnostic based on Interpolation Method in Autoregressive Models

  • Cho, Sin-Sup (Department of Computer Science and Statistics, Seoul National University, Seoul 151-742) ;
  • Ryu, Gui-Yeol (Management Research Lab, Korea Telecom Reseach Center, Seoul 137-792) ;
  • Park, Byeong-Uk (Department of Computer Science and Statistics, Seoul National University, Seoul 151-742) ;
  • Lee, Jae-June (Department of Statistics, Inha University, Inchon 402-752)
  • Published : 1993.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

An outlier detection diagnostic for the detection of k-consecutive atypical observations is considered. The proposed diagnostic is based on the innovational variance estimate utilizing both the interpolated and the predicted residuals. We adopt the interpolation method to construct the proposed diagnostic by replacing atypical observations. The perfomance of the proposed diagnositc is investigated by simulation. A real example is presented.

Keywords

References

  1. Unpublished Ph.D.dissertation, University of Washington, Department of Statistics Diagnostics for Time Series Models Bruce,A.G.
  2. Journal of the Royal Statistical Society, Ser. B v.51 Leave-k-out diagnostics for time series (with discussion) Bruce,A.G.;Martin,R.D.
  3. Unpublished Ph.D.dissertation, University of Wisconsin-Madison, Department of Statistics Outliers in time series Chang,I.
  4. Technometrics v.30 Estimation of time series parameters in the presence of outliers Chang,I.;Tiao,G.C.;Chen,C.
  5. Sankhya, A v.43 Asymptotic theory for time series containing missing and amplitude modulated observations Dunsmuir,W.;Robinson,P.M.
  6. Journal of the Royal Statistical Society, Ser. B v.32 Outliers in time series Fox,A.J.
  7. Introduction to Statistical Time Series Fuller,W.A.
  8. Journal of the American Statistical Association v.79 Estimating missing observations in economic time series Harvey,A.C.;Pierse,R.G.
  9. Journal of the Royal Statistical Society, Ser. B v.51 Comment on Leave-k-out Diagnostics for Time Series by Bruce Ledolter,J.
  10. Journal of Time Series Analysis v.11 Outlier Diagnostics in Time Series Anaysis Ledolter,J.
  11. Unpublished Ph.D.dissertation, University of Wisconsin-Madison, Department of Statistics A Study on Influential Observations in Linear Regression and Time Series Lee,J.J.
  12. Directions in Time Series Robust methods for time series Martin,R.D.;D.F.Findley(ed.)
  13. The Annals of Statistics v.14 Influence functional for time series (with discussion) Martin,R.D.;Yohai,V.J.
  14. Journal of Business & Economic Statistics v.8 Influential observations in time series Pena,D.
  15. Journal of Time Series Analysis v.10 Estimation and interpolation of missing values of stationary time series Pourahmadi,M.
  16. Unpublished Ph.D.dissertation, Seoul National University, Department of Computer Science and Statistics Outlier Detection Diagnostic in Time Series Ryu,G.Y.
  17. Technical Report, Department of Statistics, Canegie-Mellon University, Pittsburgh Effects of outliers in time series Tsay,R.S.
  18. Journal of the American Statistical Association v.81 Time series model specification in the presence of outliers Tsay,R.S.
  19. Journal of Forecasting v.7 Outliers, Level Shifts, and Variance Changes in Time Series Tsay,R.S.