Summary
A stochastic complexity approach for model selection in robust linear regression is studied in this paper. Computational aspects and applications of this approach are the focuses of the study. Particularly, we provide both procedures and a package of S language programs for computing the stochastic complexity and for proceeding with the associated model selection. On the other hand, we discuss how a probability distribution on the set of candidate models may be induced by stochastic complexity and how this distribution may be used in diagnosis to measure the likelihood that a candidate model is selected. We also discuss some strategies for model selection when large number of potential explanatory variables are available. Finally, examples and a simulation study are presented for assessing the finite sample performance of our methods.
Similar content being viewed by others
Notes
2Strictly saying, just specifying which Xi’s are included determines only a regression model class with the associated βi’s to be given. A regression model class determined by those including X1, X2 and X3 is a correct class because it contains the true model (19). Since β is mostly unknown and is uniquely estimated by the underlying regression procedure, such a correct model class may be called a correct model for purpose of conciseness.
References
Becker, R., Chambers, J.M. & Wilks, A. (1988), The New S language, Wadsworth, Belmont CA.
George, E.I. & McCulloch, R.E. (1997), ‘Approaches for Bayesian variable selection’, Statistica Sinica 7, 339–373.
Glantz, S.A. & Slinker, B.K. (1990), Primer of Applied Regression and Analysis of Variance, McGraw-Hill, Inc., New York.
Hampel, F.R. (1974), ‘The influence curve and its role in robust estimation’, J. Amer. Statist Assoc. 69, 383–393.
Hampel, F.R. (1983), ‘Some aspects of model choice in robust statistics’, Proceedings of the 44th Session of ISI, Book 2, Madrid, 767–771.
Hampel, F.R., Ronchetti, E. M., Rousseeuw, P. J. & Stahel, W. A. (1986), Robust Statistics: The Approach Based on Influence Functions, Wiley, New York.
Hill, R.W. (1977), Robust regression when there are outliers in the carriers, Ph.D. thesis, Harvard University, Cambridge, Mass..
Huber, P.J. (1964), ‘Robust estimation of a location parameter’, Ann. Math. Stat. 35, 73–101.
Huber, P.J. (1981), Robust Statistics, Wiley, New York.
Kohrt, W.M., Morgan, D.W., Bates, B. & Skinner, J.S. (1987), ‘Physiological responses of triathletes to maximal swimming, cycling, and running.’, Med. Sci. Sports Exerc. 19, 51–55.
Machado, J.A.F. (1993), ‘Robust Model Selection and M-estimation’, Econ-Ther. 9, 478–493.
Madigan, D. & York, J. (1995), ‘Bayesian graphical models for discrete data’, Internat. Statist Rev. 63, 215–232.
Miller, A.J. (1990), Subset Selection in Regression, New York: Chapman and Hall.
Qian, G., & Künsch, H. (1996), ‘On model selection in robust linear regression’, Res. rep. No. 80, Seminar für Statistik, Swiss Federal Institute of Technology, Zürich (ETH). To appear in J. Stat. Plan. & Infer..
Qian, G., & Künsch, H. (1998), ‘Some notes on Rissanen’s stochastic complexity.’, IEEE Trans. Inform. Theory. 44, 782–786.
Rao, C.R. & Wu, Y. (1989), ‘A strongly consistent procedure for model selection in a regression problem’, Biometrika 76, 369–374.
Rissanen, J. (1986), ‘Stochastic complexity and modeling’, Annals of Statistics, 14, 3, 1080–1100.
Rissanen, J. (1987), ‘Stochastic complexity (with discussion)’, J. R. Statist. Soc., Ser. B, 49, 3, 223–265.
Rissanen J. (1989), Stochastic Complexity in Statistical Inquiry, World Scientific Publishing Co. Pte. Ltd., Singapore.
Rissanen, J. (1996), ‘Fisher information and stochastic complexity’, IEEE Trans. Inform. Theory. 42, 40–47.
Ronchetti, E. (1985), ‘Robust model selection in regression’, Stat. Prob. Lett. 3, 21–23.
Ronchetti, E. & Staudte, R.G. (1994), ‘A robust version of Mallows’s Cp’, J. Amer. Statist Assoc. 89, 550–559.
Smith, A.F.M. & Roberts, G.O. (1993), ‘Bayesian computation via the Gibbs sampler and related Markov chain Monte Carlo methods’, J. Roy. Statist. Soc. Ser. B 55, 3–23.
Tanner, M.A. (1996), Tools for Statistical Inference, 3rd Edition. Springer-Verlag, New York.
Venables, W.N. & Ripley, B.D. (1994), Modern Applied Statistics with S-Plus, Springer-Verlag, New York.
Weisberg, S. (1985), Applied Linear Regression (2nd ed.), Wiley, New York.
Acknowledgment
I am grateful to an anonymous referee for the useful comments on the first version of the paper.
Author information
Authors and Affiliations
Additional information
Research supported by the La Trobe University Central Starter Grant No. 09526.
Appendix. Proof of Inequality (9)
Appendix. Proof of Inequality (9)
Define = F(h) = ρc(t+h) − ρc(t) -− hψc(t) − min{1/2, c(c+∣t∣)−1}h2 for any given t. Straightforward calculations give the following expressions: When t≥ c
When t ≤ −c
When ∣t∣| < c
It is easy to show that each of the above expressions is not great than 0. For example, given that t ≥ c and h ≤ − c − t, we have F(−c − t) = c2 − ct ≤ 0 and F′(h) = −2c(c+t+ h)(c +t)−1 ≥ 0, thus F(h) ≥ 0. Therefore, the assertion of (9) follows.
Rights and permissions
About this article
Cite this article
Qian, G. Computations and analysis in robust regression model selection using stochastic complexity. Computational Statistics 14, 293–314 (1999). https://doi.org/10.1007/BF03500911
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF03500911