Statistical Science

Robust Analysis of Linear Models

Joseph W. McKean

Full-text: Open access


This paper presents three lectures on a robust analysis of linear models. One of the main goals of these lectures is to show that this analysis, similar to the traditional least squares-based analysis, offers the user a unified methodology for inference procedures in general linear models. This discussion is facilitated throughout by the simple geometry underlying the analysis. The traditional analysis is based on the least squares fit which minimizes the Euclidean norm, while the robust analysis is based on a fit which minimizes another norm. Several examples involving real data sets are used in the lectures to help motivate the discussion.

Article information

Statist. Sci. Volume 19, Number 4 (2004), 562-570.

First available in Project Euclid: 18 April 2005

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Asymptotic relative efficiency breakdown point diagnostics influence function least squares linear hypotheses nonparametrics norms rank-based analysis robustness Wilcoxon scores


McKean, Joseph W. Robust Analysis of Linear Models. Statist. Sci. 19 (2004), no. 4, 562--570. doi:10.1214/088342304000000549.

Export citation


  • Abebe, A., Crimin, K., McKean, J. W., Haas, J. V. and Vidmar, T. J. (2001). Rank-based procedures for linear models: Applications to pharmaceutical science data. Drug Information J. 35 947--971.
  • Crimin, K., Abebe, A. and McKean, J. W. (2003). Robust general linear models and graphics via a user interface. Unpublished manuscript.
  • Hampel, F. R., Ronchetti, E. M., Rousseeuw, P. J. and Stahel, W. J. (1986). Robust Statistics. The Approach Based on Influence Functions. Wiley, New York.
  • Hettmansperger, T. P. and McKean, J. W. (1998). Robust Nonparametric Statistical Methods. Arnold, London.
  • Hettmansperger, T. P., McKean, J. W. and Sheather, S. J. (2000). Robust nonparametric methods. J. Amer. Statist. Assoc. 95 1308--1312.
  • Hollander, M. and Wolfe, D. A. (1999). Nonparametric Statistical Methods, 2nd ed. Wiley, New York.
  • Huber, P. J. (1981). Robust Statistics. Wiley, New York.
  • McKean, J. W., Naranjo, J. D. and Sheather, S. J. (1999). Diagnostics for comparing robust and least squares fits. J. Nonparametr. Statist. 11 161--188.
  • McKean, J. W., Sheather, S. J. and Hettmansperger, T. P. (1993). The use and interpretation of residuals based on robust estimation. J. Amer. Statist. Assoc. 88 1254--1263.
  • Rousseeuw, P. J. and Leroy, A. M. (1987). Robust Regression and Outlier Detection. Wiley, New York.
  • Rousseeuw, P. J. and Van Driessen, K. (1999). A fast algorithm for the minimum covariance determinant estimator. Technometrics 41 212--223.
  • Simpson, D. G., Ruppert, D. and Carroll, R. J. (1992). On one-step GM-estimates and stability of inferences in linear regression. J. Amer. Statist. Assoc. 87 439--450.
  • Terpstra, J. T. and McKean, J. W. (2004). Rank-based analysis of linear models using R. Technical Report 151, Statistical Computation Lab, Western Michigan Univ.