Abstract
In recent years a great deal of research has been devoted to developing complex regression models that allow to deal simultaneously with nonlinear covariate effects and spatial heterogeneity. Such models are referred to as geoadditive models. These models may routinely be estimated using standard statistical software packages. Much less effort, however, has been spent to model and variable selection in the context of complex regression models. In this article we develop an empirical Bayes approach for simultaneous selection of variables and the degree of smoothness in geoadditive models. Our approach allows to decide whether a particular continuous covariate enters the model linearly or nonlinearly or is removed from the model and whether a spatial effect should be added to the model or not.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
BESAG, J., YORK, J. and MOLLIE, A. (1991): Bayesian Image Restoration with Two Applications in Spatial Statistics. Annals of the Inst. of Statistical Mathematics, 43, 1–59.
BREZGER, A., KNEIB, T. and LANG, S. (2005): BayesX Manuals. Available at http://www.stat.uni-muenchen.de/~bayesx/bayesx.html.
DENUIT, M. and LANG, S. (2004): Nonlife Ratemaking with Bayesian GAM’s. Insurance: Mathematics and Economics, 35, 627–647.
EILERS, P.H.C. and MARX, B.D. (1996): Flexible Smoothing Using B-splines and Penalties. Statistical Science, 11, 89–121.
FAHRMEIR, L. and LANG, S. (2001): Bayesian Inference for Generalized Additive Mixed Models Based on Markov Random Field Priors. Journal of the Royal Statistical Society C, 50, 201–220.
HASTIE, T. and TIBSHIRANI, R. (1990): Generalized Additive Models. Chapman & Hall, London.
KAMMANN, E.E. and WAND, M.P. (2003): Geoadditive Models. Journal of the Royal Statistical Society C, 52, 1–18.
LANG, S. and BREZGER, A. (2004): Bayesian P-splines. Journal of Computational and Graphical Statistics, 13, 183–212.
TUTZ, G. and BINDER, H. (2005): Boosting Ridge Regression. SFB 386 Discussion Paper 418.
WOOD, S. (2004): The mgcv Package. Available at http://www.r-project.org/.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Belitz, C., Lang, S. (2007). Simultaneous Selection of Variables and Smoothing Parameters in Geoadditive Regression Models. In: Decker, R., Lenz, H.J. (eds) Advances in Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70981-7_22
Download citation
DOI: https://doi.org/10.1007/978-3-540-70981-7_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70980-0
Online ISBN: 978-3-540-70981-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)