The Forward Sequential Procedure for the Identifying Multiple Outliers in Linear Regression

  • Park, Jin-Pyo (Division of Computer engineering and science, Kyungnam University)
  • Published : 2005.11.30

Abstract

In this paper we consider the problem of identifying and testing outliers in linear regression. First we consider the use of the so-called scale ratio tests for testing the null hypothesis of no outliers. This test is based on the ratio of two residual scale estimates. We show the asymptotic distribution of the test statistics and investigate its properties. Next we consider the problem of identifying the outliers. A forward sequential procedure using the suggested test is proposed. The new method is compared with classical procedure in the real data example. Unlike other forward procedures, the present one is unaffected by masking and swamping effects because the test statistic is based on robust scale estimate.

Keywords

References

  1. Statistical Theory and Methodology in Science and Engineering Brownlee, K.A.
  2. Applied Regression Analysis Draper, N.R.;Smith, H.
  3. J. Am. Stat. Assoc. v.79 Least median of squares regression Rousseeuw, P.J.;Yohai, V.
  4. Robust regression and outlier detection Rousseeuw, P.J.;Leroy, A.M.
  5. Hyperinflation and Nationalist China, Stability and Inflation, and A .Volume of Essays to Honour the memory of A. W. H. Phillips Simkin, C.G.F.
  6. Jour, of statist. Inf. and Planning Optimal locally robust M-estimates of regression Yohai, V.J.;Zamar