Advertisement

Statistics and Computing

, Volume 9, Issue 4, pp 251–263 | Cite as

Computing least trimmed squares regression with the forward search

  • A. C. Atkinson
  • T.-C. Cheng
Article

Abstract

Least trimmed squares (LTS) provides a parametric family of high breakdown estimators in regression with better asymptotic properties than least median of squares (LMS) estimators. We adapt the forward search algorithm of Atkinson (1994) to LTS and provide methods for determining the amount of data to be trimmed. We examine the efficiency of different trimming proportions by simulation and demonstrate the increasing efficiency of parameter estimation as larger proportions of data are fitted using the LTS criterion. Some standard data examples are analysed. One shows that LTS provides more stable solutions than LMS.

Detection of outliers forward search algorithm high breakdown point least trimmed squares regression diagnostics stalactite plot 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Atkinson, A. C. (1985) Plots, Transformations and Regression, Oxford: Oxford University Press.Google Scholar
  2. Atkinson, A. C. (1994) Fast very robust methods for the detection of multiple outliers. Journal of the American Statistical Association, 89, 1329–1339.Google Scholar
  3. Atkinson, A. C. and Mulira, H.-M. (1993) The stalactite plot for the detection of multivariate outliers. Statistics and Computing, 3, 27–35.Google Scholar
  4. Coakley, C. W., Mili, L. and Cheniae, M. G. (1994) Effect of leverage on the finite sample effciencies of high breakdown estimators. Statistics and Probability Letters, 19, 399–408.Google Scholar
  5. Croux, C., Rousseeuw, P. J. and Hössjer, O. (1994) Generalized S-estimators. Journal of the American Statistical Association, 89, 1271–1281.Google Scholar
  6. Davies, L. (1994) Desirable properties, breakdown and effciency in the linear regression model. Statistics and Probability Letters, 19, 361–370.Google Scholar
  7. Davies, P. L. (1993) Aspects of robust linear regression. The Annals of Statistics, 21, 1843–1899.Google Scholar
  8. Hadi, A. S. and Luceño, A. (1997) Maximum trimmed likelihood estimators: a unified approach, examples, and algorithms. Computational Statistics and Data Analysis, 25, 251–272.Google Scholar
  9. Hawkins, D. M. (1994) The feasible solution algorithm for least trimmed squares regression. Computational Statistics and Data Analysis, 17, 185–196.Google Scholar
  10. Hettmansperger, T. P. and McKean, J. W. (1998) Robust Nonparametric Statistical Methods, London: Arnold.Google Scholar
  11. Hettmansperger, T. P. and Sheather, S. J. (1992) A cautionary note on the method of the least median squares. The American Statistician, 46, 79–83.Google Scholar
  12. Hettmansperger, T. P. and Sheather, S. J. (1993) Reply to the comment of Rousseeuw, P. J., The American Statistician, 47, 162–163.Google Scholar
  13. Hössjer, O. (1994) Rank-based estimates in the linear model With high breakdown point. Journal of the American Statistical Association, 89, 149–157.Google Scholar
  14. Hössjer, O. (1995) Exact computation of the least trimmed squares estimate in simple linear regression. Computational Statistics and Data Analysis, 19, 265–282.Google Scholar
  15. Morgenthaler, S. (1991) A note on effcient regression estimators with positive breakdown point. Statistics and Probability Letters, 11, 469–472.Google Scholar
  16. Rousseeuw, P. J. (1984) Least median of squares regression. Journal of the American Statistical Association, 79, 871–880.Google Scholar
  17. Rousseeuw, P. J. (1993) Comment on the paper of Hettmansperger, T. P. and Sheather, S. J., The American Statistician, 47, 162.Google Scholar
  18. Rousseeuw, P. J. (1994) Unconventional features of positivebreakdown estimators. Statistics and Probability Letters, 19, 417–431.Google Scholar
  19. Rousseeuw, P. J. and Leroy, A. M. (1987) Robust Regression and Outlier Detection, New York: John Wiley.Google Scholar
  20. Stefanski, L. A. (1991) A note on high breakdown point estimators. Statistics and Probability Letters, 11, 353–358.Google Scholar
  21. Yohai, V. J. (1987) High breakdown point and high effciency robust estimators for regression. The Annals of Statistics, 15, 462–656.Google Scholar
  22. Yohai, V. J. and Zamar, R. H. (1988) High breakdown point estimates of regression by means of the minimization of an effcient scale. Journal of the American Statistical Association, 83, 406–413.Google Scholar

Copyright information

© Kluwer Academic Publishers 1999

Authors and Affiliations

  • A. C. Atkinson
  • T.-C. Cheng

There are no affiliations available

Personalised recommendations