Abstract

We consider two methods of defining a regression analogue to a trimmed mean. The first was suggested by Koenker and Bassett and uses their concept of regression quantiles. that of a trimmed mean. Its asymptotic behavior is completely analogous to The second method uses residuals from a preliminary estimator. Its asymptotic behavior depends heavily on the preliminary estimate; it behaves, in general, quite differently than the estimator proposed by Koenker and Bassett, and it can be rather inefficient at the normal model even if the percent trimming is small. However, if the preliminary estimator is the average of the two regression quantiles used with Koenker and Bassett's estimator, then the first and second methods are asymptotically equivalent for sYmmetric error distributions. Key Words and Phrases: regression analogue, trimmed mean, regression quantile, preliminary estimator, linear model, trimmed least squares David Ruppert is an Assistant Professor and Raymond,J. Carroll an

Citations

2261	Convergence of probability measures - Billingsley - 1999
212	Regression quantiles - Koenker, Bassett - 1978
47	A note on quantiles in large samples - BAHADUR - 1966
35	Robust Estimates of Location: Survey and advances - Andrews, Bickel, et al. - 1972
32	One-step Huber estimates in linear models - Bickel - 1975
31	A survey of sampling from contaminated distributions. Contributions to Probability and Statistics (in: I. Olkin et al., eds - Tukey - 1960
28	Robust Statistical Procedures - Huber - 1977
24	Adaptive robust procedures: A partial review and some suggestions for future applications and theory (with discussion - HOGG - 1974
15	Asymptotic relations of M-estimates and R-estimates in linear regression - Jurěcková - 1977
14	A new proof of the Bahadur representation of quantiles and an application - GHOSH - 1971
12	Examination of residuals - Anscombe - 1961
12	On estimating variances of robust estimators when the errors are asymmetric - Carroll - 1979
11	Less Vulnerable Confidence and Significance Procedures for Location Based on a Single Sample: Trimming/Winsorization 1 - Tukey, McLaughlin - 1963
8	Robust Estimation - Huber - 1981
7	A M (1976) Confidence interval robustness with long-tailed symmetric distributions - Gross
7	Do robust estimators work with real data - Stigler - 1977
5	On Some Analogues to Linear Combinations of Order Statistics in the Linear Model," The Annals of Statistics - Bickel - 1973
4	Robust estimates of location: symmetry and asymmetric contamination - Jaeckel - 1971
3	Almost Sure Properties of Robust Regression Estimates, Unpublished manuscript - Carroll, Ruppert - 1979
2	An asymptotic representation of trimmed means with applications - WET, VENTER - 1974
2	A Monte-Carlo swindle for estimators of location - Gross - 1973
2	A Student Oriented Preprocessor for MPS/360 - McKeown, Rubin - 1977
1	Robust regres~ion by trimmed least squares estimation - Ruppert, Carroll - 1978
1	CONTROLLING OFFICE NAME AND ADDRESS 12. REPORT DATE Air Force Office of Scientific Research February 1980 Bolling Air Force Base 13 - NUMBERS