James-Stein-Type Estimators in Large Samples With Application to the Least Absolute Deviations Estimator
Authors:
- 1 June 2001
- journal article
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 96 (454) , 697-705
Abstract
We explore the extension of James–Stein–type estimators in a direction that enables them to preserve their superiority when the sample size goes to infinity. Instead of shrinking a base estimator toward a fixed point, we shrink it toward a data-dependent point. We provide an analytic expression for the asymptotic risk and bias of James–Stein–type estimators shrunk toward a data-dependent point and prove that they have smaller asymptotic risk than the base estimator. Shrinking an estimator toward a data-dependent point turns out to be equivalent to combining two random variables using the James–Stein rule. We propose a general combination scheme that includes random combination (the James–Stein combination) and the usual nonrandom combination as special cases. As an example, we apply our method to combine the least absolute deviations estimator and the least squares estimator. Our simulation study indicates that the resulting combination estimators have desirable finite-sample properties when errors are drawn from symmetric distributions. Finally, using stock return data, we present some empirical evidence that the combination estimators have the potential to improve out-of-sample prediction in terms of both mean squared error and mean absolute error.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Heuristics of instability and stabilization in model selectionThe Annals of Statistics, 1996
- Better Subset Regression Using the Nonnegative GarroteTechnometrics, 1995
- Determination of Estimators with Minimum Asymptotic Covariance MatricesEconometric Theory, 1993
- A James-Stein Type Estimator for Combining Unbiased and Possibly Biased EstimatorsJournal of the American Statistical Association, 1991
- Relative performance of stein-rule and preliminary test estimators in linear models least squares theoryCommunications in Statistics - Theory and Methods, 1987
- On shrinkage r-estimation in a multiple regression modelCommunications in Statistics - Theory and Methods, 1986
- On Some Shrinkage Estimators of Multivariate LocationThe Annals of Statistics, 1985
- On shrinkage m-estimators of location parametersCommunications in Statistics - Theory and Methods, 1985
- Combining Estimates of LocationJournal of the American Statistical Association, 1976
- Algorithm 478: Solution of an Overdetermined System of Equations in the l1 Norm [F4]Communications of the ACM, 1974