Boosting for Estimating Spatially Structured Additive Models



Spatially structured additivemodels offer the flexibility to estimate regression relationships for spatially and temporally correlated data. Here, we focus on the estimation of conditional deer browsing probabilities in the National Park “Bayerischer Wald”. The models are fitted using a componentwise boosting algorithm. Smooth and non-smooth base learners for the spatial component of the models are compared. A benchmark comparison indicates that browsing intensities may be best described by non-smooth base learners allowing for abrupt changes in the regression relationship.


Generalize Additive Model Ensemble Method Generalize Additive Model Model Browse Tree Smooth Relationship 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Ammer, C. (1996). Impact of ungulates on structure and dynamics of natural regeneration of mixed mountain forests in the Bavarian Alps, Forest Ecology and Management 88: 43–53.CrossRefGoogle Scholar
  2. Augustin, N., Musio, M., von Wilpert E, K., Kublin, Wood, S. & Schumacher, M. (2009). Modelling spatio-temporal forest health monitoring data.Google Scholar
  3. Breiman, L. (1996). Bagging predictors, Machine Learning 24: 123–140.zbMATHMathSciNetGoogle Scholar
  4. Breiman, L. (2001). Random forests, Machine Learning 45: 5–32.zbMATHCrossRefGoogle Scholar
  5. Breiman, L., Friedman, J., Olshen, R. & Stone, C. (1983). Classification and regression trees, Wadsworth, Belmont, California .Google Scholar
  6. Bühlmann, P. (2004). Bagging, boosting and ensemble methods, in J. Gentle, W. Härdle & Y.Mori (eds), Handbook of Computational Statistics: Concepts and Methods, Springer.Google Scholar
  7. Bühlmann, P. & Hothorn, T. (2007). Boosting algorithms: Regularization, prediction and model fitting, Statistical Science 22(4): 477–505.CrossRefMathSciNetGoogle Scholar
  8. Bühlmann, P. & Yu, B. (2003). Boosting with the l 2 loss: Regression and classification, Journal of the American Statistical Association 98: 324–339.zbMATHCrossRefMathSciNetGoogle Scholar
  9. Efron, B. (1979). Bootstrap methods: another look at the jackknife, Annals of Statistics 7: 1–26.zbMATHCrossRefMathSciNetGoogle Scholar
  10. Eiberle, K. (1989). Über den Einfluss des Wildverbisses auf die Mortalität von jungen Waldbämen in der oberen Montanstufe, Schweizer Zeitschrift für Forstwesen 140: 1031–1042.Google Scholar
  11. Eiberle, K. & Nigg, H. (1987). Grundlagen zur Beurteilung des Wildverbisses im Gebirgswald, Schweizer Zeitschrift für Forstwesen 138: 474–785.Google Scholar
  12. Eilers, P. & Marx, B. (1996). Flexible smoothing with B-splines and penalties, Statistical Science 11: 89–102.zbMATHCrossRefMathSciNetGoogle Scholar
  13. Fahrmeir, L., Kneib, T. & Lang, S. (2004). Penalized structured additive regression for space-time data: A Bayesian perspective, Statistica Sinica 14: 731–761.zbMATHMathSciNetGoogle Scholar
  14. Forstliches Gutachten (2006). Forstliche Gutachten zur Situation der Waldverjungung 2006, Bayerische Staatsministerium für Landwirtschaft und Forsten.Google Scholar
  15. Friedman, J. (2001). Greedy function approximation: A gradient boosting machine, The Annals of Statistics 29: 1189–1232.zbMATHCrossRefMathSciNetGoogle Scholar
  16. Fritz, P. (2006). Ökologischer Waldumbau in Deutschland - Fragen, Antworten, Perspektiven, Oekom, München.Google Scholar
  17. Hastie, T. & Tibshirani, R. (1990). Generalized Additive Models, Chapman & Hall/CRC.Google Scholar
  18. Hastie, T., Tibshirani, R. & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer.Google Scholar
  19. Hothorn, T., Hornik, K. & Zeileis, A. (2006). Unbiased recursive partitioning: A conditional inference framework, Journal of Computational and Graphical Statistics 15: 651–674.CrossRefMathSciNetGoogle Scholar
  20. Kneib, T., Hothorn, T. & Tutz, G. (2009). Variable selection and model choice in geoadditive regression models, Biometrics 65: 626–634.zbMATHCrossRefGoogle Scholar
  21. Knoke, T., Ammer, C., Stimm, B. & Mosandl, R. (2008). Admixing broad-leaved to coniferous tree species–A review on yield, ecological stability and economics, European Journal of Forest Research 127: 89–101.CrossRefGoogle Scholar
  22. Knoke, T. & Seifert, T. (2008). Integrating selected ecological effects of mixed european beech–Norway spruce stands in bioeconomic modelling, Ecological Modelling 210: 487–498.CrossRefGoogle Scholar
  23. Lutz, R., Kalisch, M. & Bühlmann, P. (2008). Robustified l 2 boosting, Computational Statistics & Data Analysis 52: 3331–3341.zbMATHCrossRefMathSciNetGoogle Scholar
  24. Moog, M. (2008). Bewertung von Wildschäden im Wald, Neumann-Neudamm, Melsungen.Google Scholar
  25. Motta, R. (2003). Ungulate impact on rowan (Sorbus aucuparia l) and norway spruce (Picea abies (l) karst) height structure in mountain forests in the italian alps, Forest Ecology and Management 181: 139–150.CrossRefGoogle Scholar
  26. Prien, S. (1997). Wildschäden im Wald, Paul Parey, Berlin.Google Scholar
  27. Rüegg, D. (1999). Zur Erhebung des Einflusses von Wildtieren auf die Waldverüngung, Schweizer Zeitschrift für Forstwesen 150: 327–331.CrossRefGoogle Scholar
  28. Schmid, M. & Hothorn, T. (2008). Boosting additive models using component-wise P-splines, Computational Statistics & Data Analysis 53: 298–311.CrossRefGoogle Scholar
  29. Weisberg, P., Bonavia, F. & Bugmann, H. (2005). Modeling the interacting effects of browsing and shading on mountain forest regeneration (Picea abies), Ecological Modelling 185: 213–230.CrossRefGoogle Scholar
  30. Wood, S. (2006). Generalized Additive Models: An Introduction with R, Chapman & Hall/CRC.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  1. 1.Institut für StatistikLudwig-Maximilians-Universität MünchenMünchenGermany

Personalised recommendations