Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지

Influence Assessment in Robust Regression

  • Published : 1997.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Robust regression based on M-estimator reduces and/or bounds the influence of outliers in the y-direction only. Therefore, when several influential observations exist, diagnostics in the robust regression is required in order to detect them. In this paper, we propose influence diagnostics in the robust regression based on M-estimator and its one-step version. Noting that M-estimator can be obtained through iterative weighted least squares regression by using internal weights, we apply the weighted least squares (WLS) regression diagnostics to robust regression.

Keywords

References

  1. Journal of Royal Statistical Society, B v.44 Regression diagnostics, transformations and constructed variables Atkinson, A.C.
  2. Journal of American Statistical Association v.70 One-step Huber estimator in the linear model Bickel, D.J.
  3. Technometrics v.19 Detection of influential observations in linear regression Cook, R.D.
  4. Residuals and Influence in Regression Cook, R.D.;Weisberg, S.
  5. Journal of Royal Statistical Society, B v.48 Assessment of local influence Cook, R.D.
  6. Mathematicsche Operations for Schung and Statistic, Series Statistics v.8 Robust methods of estimation of regression coefficients Huber, P.J.
  7. Journal of the Korean Statistical Society v.19 A local influence approach to regression diagnostics with application to robust regression Huh, M.H.;Park, S.H.
  8. Exploring Data Tables, Trends and Shapes Robust regression Li, G.;D.C. Hoaglin(ed.);F. Mosteller(ed.);J.W. Tukey(ed.)
  9. Robust Regression and Outlier Detection Rousseeuw, D.J.;Leroy, A.M.
  10. Doctoral Thesis, Dept. of Statistics, Korea University Weighted Least Squares Regression Diagnostics and its Application to Robust Regression Sohn, B.Y.