Instability of least squares, least absolute deviation and least median of squares linear regression

Statistical Science

Volumn 13, Issue 4, 1998, Pages 337-350

  Ellis, Steven P ^a  

^a NEW YORK STATE PSYCHIATRIC INSTITUTE   (United States)

Author keywords

Collinearity; Singularity; Stability

Indexed keywords

EID: 0001041317     PISSN: 08834237     EISSN: None     Source Type: Journal    
DOI: 10.1214/ss/1028905829     Document Type: Article

References (15)

1. BELSLEY, D. A. (1991). Conditioning Diagnostics: Collinearity and Weak Data in Regression. Wiley, New York.
2. 1 regression in the light of linear programming. In L i-Statistical Analysis and Related Methods (Y. Dodge, ed.) 47-61. North-Holland, Amsterdam.
3. Ellis, S. P. and Morgenthaler S. (1992). Leverage and breakdown in L1 regression. J. Amer. Statist. Assoc. 87 143-148.
4. Freedman, F., Pisani, R., Purves, R. and Adhikari, A. (1991). Statistics, 2nd ed. Norton, New York.
5. Koenker, R. (1994). Confidence intervals for regression quan-tiles. In Asymptotic Statistics: Proceedings of the 5th Prague Symposium (P. Mandl and M. Huskova, eds.) 349-359. Springer, Berlin.
6. Mizera, I. (1998). On continuity: resistance and qualitative robustness. Preprint. (Available at http://www.uniba.sk/mizera.)
7. Portnoy, S. (1991a). Asymptotic behavior of the number of regression quantile breakpoints. SIAM J. Sci. Statist. Comput. 12 867-883.
8. Portnoy, S. (1991b). Asymptotic behavior of regression quan-tiles in nonstationary, dependent cases. J. Multivariate Anal. 38 100-113.
9. Portnoy, S. and Welsh, A. (1992). Exactly what is being modelled by the systematic component of a heteroscedastic linear regression. Statist. Probab. Lett. 13 253-258.
10. Rockafellar, R. T. and Wets, R. J.-B. (1998). Variational Analysis. Springer, Berlin.
11. Simmons, G. F. (1963). Introduction to Topology and Modern Analysis. McGraw-Hill, New York.
12. Spady, R. (1991). Saddlepoint approximations for regression models. Biometrika 78 879-889.
13. Venables, W. N. and Ripley, B. D. (1994). Modern Applied Statistics with S-Plus. Springer, New York.
14. Zhou, Q. and Portnoy, S. (1996). Direct use of regression quan-tiles to construct confidence sets for linear models. Ann. Statist. 24 287-306.
15. Zhou, Q. and Portnoy, S. (1998). Statistical inference on het-eroscedastic linear models based on regression quantiles. J. Nonparametr. Statist. 9 239-260.