Summary
An asymptotically efficient selection of regression variables is considered in the situation where the statistician estimates regression parameters by the maximum likelihood method but fails to choose a likelihood function matching the true error distribution. The proposed procedure is useful when a robust regression technique is applied but the data in fact do not require that treatment. Examples and a Monte Carlo study are presented and relationships to other selectors such as Mallows'Cp are investigated.
Similar content being viewed by others
References
Akaike, H. (1970). Statistical predictor identification,Ann. Inst. Statist. Math.,22, 203–217.
Andrews, D. F., Bickel, P. J., Hampel, F., Huber, P., Rogers, W. and Tukey, J. W. (1972).Robust Estimation of Location, Princeton University Press, Princeton.
Breiman, L. and Freedman D. (1983). How many variables should be entered in a regression equation.J. Amer. Statist. Ass.,78, 131–136.
Cox, D. (1983). Asymptotics forM-type smoothing splines,Ann. Statist.,11, 530–551.
Härdle, W. (1984). Robust regression function estimation,J. Multivariate Anal.,14, 169–180.
Huber, P. (1973). Robust regression: Asymptotics, conjectures and Monte Carlo,Ann. Statist.,1, 799–821.
Huber, P. (1981).Robust Statistics, Wiley, New York.
Li, K. C. (1984). Asymptotic optimality forCp,C1, cross-validation and generalized cross-validation: Discrete, index set, Manuscript.
Mallows, C. (1973). Some comments onCp,Technometrics,15, 661–675.
Ronchetti, E. (1985). Robust model selection in regression,Statist. Prob. Letters,3, 21–23.
Schrader, R. M. and Hettmansperger, T. P. (1980). Robust analysis of variance based upon a likelihood ratio criterion,Biometrika,67, 93–101.
Shibata, R. (1981). An optimal selection of regression variables,Biometrika,68, 45–54.
Stone, C. J. (1984). An asymptotically optimal window selection rule for kernel density estimates,Ann. Statist.,12, 1285–1297.
Whittle, P. (1960). Bounds for the moments of linear and quadratic forms in independent variables.Theor. Prob. Appl.,3, 302–305.
Author information
Authors and Affiliations
Additional information
Research supported by Deutsche Forschungsgemeinschaft, Sonderforschungsbereich 123 “Stochastische Mathematische Modelle” and AFOSR Contract No. F49620 82 C 0009.
About this article
Cite this article
Härdle, W. An effective selection of regression variables when the error distribution is incorrectly specified. Ann Inst Stat Math 39, 533–548 (1987). https://doi.org/10.1007/BF02491488
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02491488