Abstract
Sliced Inverse Regression (SIR) (Li, 1991) is a method for dimension reduction in (nonparametric) regression models, based on the idea of using the information contained in the inverse regression curve. In the various steps of the SIR procedure, classical statistical estimators are used. Thus, the resulting method is nonrobust, and an immediate possibility to robustify SIR is to replace the classical estimators by robust ones. This leads to procedures which maintain the clever estimation scheme of the original SIR method but can cope better with outliers in the regressor space. We present such robustified versions of SIR and compare them with the original procedure and among each other under different model assumptions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Refreence
Aragon, Y. and Saracco, J. (1997). Sliced inverse regression (SIR): An appraisal of small sample alternatives to slicing.Comput. Statist.12:109–130.
Becker, C. and Gather, U. (1999a). The largest nonidentifiable outlier: A comparison of multivariate simultaneous outlier identification rules. Submitted for Publication.
Becker, C. and Gather, U. (1999b). The masking breakdown point of multivariate outlier identification rules.J. Amer. Statist. Assoc.94:947–955.
Bedall, F. K. and Zimmermann, H. (1979). Algorithm as 143: The mediancentre.Appl. Statist.23:325–328.
Bellman, R. E. (1961). Adaptive control processes. Technical report, Princeton University Press.
Bura, E. (1997). Dimension reduction via parametric inverse regression. InL1-Statistical Procedures and Related Topicsvolume 31 ofIMS Lecture Notespages 215–228.
Carroll, R. J. and Li, K.-C. (1992). Measurement error regression with unknown link: Dimension reduction and data visualization.J. Amer. Statist. Assoc.87:1040–1050.
Chen, C.-H. and Li, K.-C. (1998). Can SIR be as popular as multiple linear regression.Statist. Sinica8:289–316.
Cook, R. D. (1994). On the interpretation of regression plots.J. Amer. Statist. Assoc.89:177–189.
Cook, R. D. (1996). Graphics for regressions with a binary response.J. Amer. Statist. Assoc.91:983–992.
Cook, R. D. (1998a). Principal hessian directions revisited.J. Amer. Statist. Assoc.93:84–100.
Cook, R. D. (1998b).Regression Graphics: Ideas for Studying Regressions through Graphics.Wiley, New York.
Cook, R. D. and Nachtsheim, C. J. (1994). Reweighting to achieve elliptically contoured covariates in regression.J. Amer. Statist. Assoc.89:592–599.
Cook, R. D. and Weisberg, S. (1991). Comment onsliced inverse regression for dimension reductionby k.c. li.J. Amer. Statist. Assoc., 86:328–332.
Cook, R. D. and Weisberg, S. (1994).An Introduction to Regression Graphics.Wiley, New York.
Croux, C. and Ruiz-Gazen, A. (1996). A fast algorithm for robust principal components based on projection pursuit. In Prat, A., editorCompstat Proceedings in Computational Statistics 12th Symposium Barcelona 1996pages 211–216. Physika-Verlag, Heidelberg.
Davies, P. L. and Gather, U. (1993). The identification of multiple outliers. invited paper with discussion and rejoinder.J. Amer. Statist. Assoc.88:782801.
Donoho, D. L. (1982).Breakdown Properties of Multivariate Location Estimators.PhD thesis, Department of Statistics, Harvard University.
Ferré, L. (1997). Dimension choice for sliced inverse regression based on ranks.Student2:95–108.
Ferré, L. (1998). Determining the dimension in sliced inverse regression and related methods.J. Amer. Statist. Assoc.93:132–140.
Friedman, J. H. (1994). An overview of predictive learning and function approximation. In V. Cherkassky, J. H. F. and Wechsler, H., editorsFrom Statistics to Neural Networks. Theory and Pattern Recognition Applicationspages 1–61. Springer, Berlin.
Gather, U. and Becker, C. (1997). Outlier identification and robust methods. In Maddala, G. S. and Rao, C. R., editorsHandbook of Statisticsvolume 15: Robust Inference, pages 123–143. Elsevier, Amsterdam.
Gather, U. and Hilker, T. (1997). A note on tyler’s modification of the MAD for the stahel-donoho estimator. Ann.Statist.25:2024–2026.
Gather, U., Hilker, T., and Becker, C. (1999). A note on outlier sensitivity of sliced inverse regression. Technical report, Department of Statistics, University of Dortmund. Preprint.
Hall, P. and Li, K.-C. (1993). On almost linearity of low dimensional projections from high dimensional data. Ann.Statist.21:867–889.
Härdle, W. and Tsybakov, A. B. (1991). Comment onsliced inverse regression for dimension reductionby k., li.J.Amer.Statist. Assoc., 86:333–335.
Hsing, T. and Carroll, R. J. (1992). An asymptotic theory for sliced inverse regression.Ann. Statist.20:1040–1061.
Kötter, T. (1996). An asymptotic result for sliced inverse regression.Comput. Statist.11:113–136.
Li, G. and Chen, Z. (1985). Projection-pursuit approach to robust dispersion matrices and principal components: Primary theory and monte carlo.J. Amer. Statist. Assoc.80:1084.
Li, K.-C. (1991). Sliced inverse regression for dimension reduction (with discussion).J. Amer. Statist. Assoc.86:316–342.
Li, K.-C. (1992). On principal hessian directions for data visualization and dimension reduction: Another application of stein’s lemma.J. Amer. Statist. Assoc.87:1025–1039.
Liu, R. Y. (1990). On a notion of data depth based on random simplices. Ann.Statist.18:405–414.
Lopuhaä, H. P. (1989). On the relation between s-estimators and m-estimators of multivariate location and covariance. Ann.Statist.17:1662–1683.
Lopuhaä, H. P. and Rousseeuw, P. J. (1991). Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. Ann.Statist.19:229–248.
Rocke, D. M. (1996). Robustness properties of s-estimators of multivariate location and shape in high dimension. Ann.Statist.24:1327–1345.
Rocke, D. M. and Woodruff, D. L. (1996). Identification of outliers in multivari-ate data.J. Amer. Statist. Assoc.91:1047–1061.
Rousseeuw, P. J. (1985). Multivariate estimation with high breakdown point. In W.Grossmann, G.Pflug, I. V. and Wertz, W., editorsMathematical Statistics and Applicationspages 283–297. Reidel, Dordrecht.
Rousseeuw, P. J. and Croux, C. (1993). Alternatives to the median absolute deviation.J. Amer. Statist. Assoc.88:1273–1283.
Rousseeuw, P. J. and Ruts, I. (1999). Boxplot, bivariate. In S.Kotz, C. R. R. and Banks, D. L., editorsEncyclopedia of Statistical Sciencespages 55–60.
Rousseeuw, P. J. and Yohai, V. (1984). Robust regression by means of s-estimators. InRobust and Nonlinear Time Series Analysisvolume 26 ofLecture Notes in Statisticspages 256–272. Springer, New York.
Saracco, J. (1997). An asymptotic theory for sliced inverse regression.Comm. Statist. — Theory Methods26:2141–2171.
Schott, J. R. (1994). Determining the dimensionality in sliced inverse regression.J. Amer. Statist. Assoc.89:141–148.
Sheather, S. J. and McKean, J. W. (1997). A comparison of procedures based on inverse regression. InL 1 -Statistical Procedures and Related Topics, volume 31of IMS Lecture Notes, pages 271–278.
Small, C. G. (1990). A surveyofmultidimensional medians.Internat. Statist. Review, 58:263–277.
Stahel, W. A. (1981). Breakdownofcovariance estimators. Technical Report Research Report 31, Fachgruppe fĂĽr Statistik, ETH ZĂĽrich.
Tyler, D. E. (1994). Finite sample breakdown pointsofprojection based multi-variate location and scatter statistics.Ann. Statist.,22:1024–1044.
Velilla, S. (1998). Assessing the number of linear components in a general re-gression problem.J. Amer. Statist. Assoc.93:1088–1098.
Zhu, L.-X. and Fang, K.-T. (1996). Asymptotics for kernel estimate of sliced inverse regression.Ann. Statist.24:1053–1068.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer Basel AG
About this paper
Cite this paper
Gather, U., Hilker, T., Becker, C. (2001). A Robustified Version of Sliced Inverse Regression. In: Fernholz, L.T., Morgenthaler, S., Stahel, W. (eds) Statistics in Genetics and in the Environmental Sciences. Trends in Mathematics. Birkhäuser, Basel. https://doi.org/10.1007/978-3-0348-8326-9_10
Download citation
DOI: https://doi.org/10.1007/978-3-0348-8326-9_10
Publisher Name: Birkhäuser, Basel
Print ISBN: 978-3-0348-9518-7
Online ISBN: 978-3-0348-8326-9
eBook Packages: Springer Book Archive