Abstract
Regression techniques with high breakdown point can withstand a substantial amount of outliers in the data. One such method is the least trimmed squares estimator. Unfortunately, its exact computation is quite difficult because the objective function may have a large number of local minima. Therefore, we have been using an approximate algorithm based on p-subsets. In this paper we prove that the algorithm shares the equivariance and good breakdown properties of the exact estimator. The same result is also valid for other high-breakdown-point estimators. Finally, the special case of one-dimensional location is discussed separately because of unexpected results concerning half samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bassett, G.W., A p-Subset Property of L1 and Regression Quantile Estimates, Computational Statistics and Data Analysis 6 (1988), pp. 297–304.
Donoho, D.L., Huber, P.J., The Notion of Breakdown Point, in A Festschrift for Erich Lehmann, edited by P. Bickel, K. Doksum, J.L. Hodges, Jr., Belmont: Wadsworth (1983).
Donoho, D.L., Johnstone, I., Rousseeuw, P.J., Stahel, W., Discussion on “Projection Pursuit” by P. Huber, Annals of Statistics, 13 (1985), pp. 496–500.
Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A., Robust Statistics, New York: John Wiley (1986).
Hawkins, D.M., Bradu, D., Kass, G.V., Location of Several Outliers in Multiple Regression Data using Elemental Sets, Technometrics, 26 (1984), pp. 197–208.
Koenker, R., Bassett, G.W., Regression Quantiles, Econometrica, 46 (1978), pp. 33–50.
Rousseeuw, P.J., Regression Techniques with High Breakdown Point, The IMS Bulletin, 12 (1983), p. 155.
Rousseeuw, P.J., Least Median of Squares Regression, Journal of the American Statistical Association, 79 (1984), pp. 871–880.
Rousseeuw, P.J., Leroy, A., PROGRESS: A Program for Robust Regression Analysis, Technical Report 201, Centrum STOO, Vrije Universiteit Brussel, Belgium (1984).
Rousseeuw, P.J., Leroy, A., Robust Regression and Outlier Detection, New York: John Wiley (1987).
Rousseeuw, P.J., Yohai, V.J., Robust Regression by Means of S-estimators, in Robust and Nonlinear Time Series Analysis edited by J. Franke, W. Härdle, R.D. Martin, Lecture Notes in Statistics No. 26, New York: Springer Verlag (1984), pp. 256–272.
Siegel, A.F., Robust Regression using Repeated Medians, Biometrika, 69 (1982), pp. 242–244.
Theil, H., A Rank-Invariant Method of Linear and Polynomial Regression Analysis (Parts 1-3), Ned.Akad. Wetensch. Proc. Ser. A, 53 (1950), pp. 386–392, 521–525, 1397–1412.
van Zomeren, B.C., A Comparison of Some High-Breakdown Regression Estimators, Computational Statistics Quarterly, 4 (1987), pp. 207–218.
Yohai, V.J., High Breakdown-Point and High Efficiency Robust Estimates for Regression, Annals of Statistics, 15 (1987), pp. 642–656.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag New York, Inc.
About this paper
Cite this paper
Rousseeuw, P.J., Bassett, G.W. (1991). Robustness of the p-Subset Algorithm for Regression with High Breakdown Point. In: Directions in Robust Statistics and Diagnostics. The IMA Volumes in Mathematics and its Applications, vol 34. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-4444-8_10
Download citation
DOI: https://doi.org/10.1007/978-1-4612-4444-8_10
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-8772-8
Online ISBN: 978-1-4612-4444-8
eBook Packages: Springer Book Archive