Abstract
Bahadur representation of the difference of estimators of regression coefficients for the full data set and for the set from which one observation was deleted is given for the M-estimators which are generated by a continuous ψ-function. The representation is invariant with respect to the scale of residuals and it indicates that the bound of the norm of the difference is proportional to the gross error sensitivity. Then for the ψ-function which corresponds to the median it is shown that the difference of the estimates for the full data and for data without one observation, although being bounded in probability, can be much larger than indicated by the gross error sensitivity.
Similar content being viewed by others
References
Atkinson A. C. (1985). Plots, Transformations and Regression: An Introduction to Graphical Methods of Diagnostic Regression Analysis, Claredon Press, Oxford.
Bates D. M. and Watts D. G. (1988). Nonlinear Regression Analysis and Its Applications, Wiley, New York.
Belsley D. A., Kuh E. and Welsch R. E. (1980). Regression Diagnostics: Identifying Influential Data and Sources of Collinearity, Wiley, New York.
Breiman L. (1968). Probability, Addison-Wesley, Reading, Massachusetts.
Chatterjee S. and Hadi A. S. (1988). Sensitivity Analysis in Linear Regression, Wiley, New York.
Cook R. D. and Weisberg S. (1982). Residuals and Influence in Regression, Chapman and Hall, London.
Csörgö M. and Révész P. (1981). Strong Approximation in Probability and Statistics, Akademia Kiadó, Budapest.
Hampel F. R., Rousseeuw P. Y., Ronchetti E. M. and Stahel W. A. (1986). Robust Statistics-The Approach Based on Influence Functions, Wiley, New York.
Hand D. J., Daly F., Lunn A. D., McConway K. J. and Ostrowski E. (1994). Handbook of Small Data Sets, Chapman & Hall, London.
Hettmansperger T. P. and Sheather S. J. (1992). A cautionary note on the method of least median squares, Amer. Statist., 46, 79–83.
Huber P. J. (1964). Robust estimation of a location parameter, Ann. Math. Statist., 35, 73–101.
Jurečková J. (1988). Constistency of M-estimators of vector parameters, Proceedings of the Fourth Prague Symposium on Asymptotic Statistics, 305–312, Charles University, Prague.
Liese F. and Vajda I. (1995). Consistency of M-estimators in general models, J. Multivariat. Anal., 50, 93–114.
Mason R. L., Gunst R. F. and Hess J. L. (1989). Statistical Design and Analysis of Experiments, Wiley, New York.
Rao C. R. and Zhao L. C. (1992). On the consistency of M-estimate in linear model obtained through an estimating equation, Statist. Probab. Lett., 14, 79–84.
Rousseeuw P. J. (1993). Unconventional features of positive-breakdown estimators, Report no. 93–26 of University of Antwerp, Department of Mathematics & Computer Science, UIA, Belgium.
Rousseeuw P. J. and Leroy A. M. (1987). Robust Regression and Outlier Detection, Wiley, New York.
Rubio, A. M. and Víšek, J. Á. (1996). A note on asymptotic linearity of M-statistics in nonlinear models, Kybernetika (to appear).
Rubio A. M., Quintana F. and Víšek J. Á. (1994). Test for differences between M-estimates of non-linear regression model. Probab. Math. Statist., 14, Facs. 2, 189–206.
Sen A. and Srivastava M. (1990). Regression Analysis: Theory, Methods and Applications, Springer, Berlin.
Štěpán J. (1987). Teorie pravděpodobnosti (Probability Theory), Academia, Prague.
Vandaele W. (1978). Participation in illegitimate activities: Erlich revisted Deterrence and Incapacitation (eds. A. Blumstein, J. Cohen and D. Nagin), 270–335, National Academy of Sciences, Washington, D.C.
Víšek J. Á. (1992a). A proposal of model selection: Stability of linear regression model, Transactions of the Eleventh Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, Volume B, 451–461, Academia, 1990, Prague.
Víšek J. Á. (1992b). Stability of regression estimates with respect to subsamples, Computational Statistics, 7, 183–203.
Víšek, J. Á. (1994). A cautionary note on the method of least median of squares reconsidered, Transactions of the Twelfth Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, 254–259, Prague.
Author information
Authors and Affiliations
About this article
Cite this article
Víšek, J.Á. Sensitivity analysis of M-estimates. Ann Inst Stat Math 48, 469–495 (1996). https://doi.org/10.1007/BF00050849
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00050849