Contributed equally to the contents of this manuscript.
Applying additive modelling and gradient boosting to assess the effects of watershed and reach characteristics on riverine assemblages
Version of Record online: 2 JUN 2011
© 2011 The Authors. Methods in Ecology and Evolution © 2011 British Ecological Society
Methods in Ecology and Evolution
Volume 3, Issue 1, pages 116–128, February 2012
How to Cite
Maloney, K. O., Schmid, M. and Weller, D. E. (2012), Applying additive modelling and gradient boosting to assess the effects of watershed and reach characteristics on riverine assemblages. Methods in Ecology and Evolution, 3: 116–128. doi: 10.1111/j.2041-210X.2011.00124.x
Correspondence site: http://www.respond2articles.com/MEE/
- Issue online: 1 FEB 2012
- Version of Record online: 2 JUN 2011
- Received 29 June 2010; accepted 28 April 2011 Handling Editor: Jana McPherson
Appendix S1. Detailed description how gradient boosting fits a GAM and a simple example of component-wise gradient boosting.
Appendix S2. Map of the Chesapeake Bay basin portion of Maryland, USA, study locations (X), and ecoregion boundaries. Inset shows the position of the study area in relation to the mid-Atlantic region of the USA.
Appendix S3. List of covariates used in model construction. *Variables that were log10 transformed prior to analyses.
Appendix S4. Mathematical formulas for transforming marginal function estimates from boosted GAMs back to the original units of the responses.
Appendix S5. Software and sample R-code used in statistical analyses.
Appendix S6. Marginal functional estimates for boosted generalized additive models for all eight response variables. For figures: black lines indicate the marginal functional estimates from the boosted GAMs using the full data set; gray lines represent marginal functional estimates obtained from 100 bootstrap samples of the full data set. Vertical lines on the x-axis indicate observed sample values. Abbreviations for predictors (x-axis) defined in Appendix S3.
Appendix S7. Marginal ecoregion effect estimates for boosted generalized additive models for benthic macroinvertebrate and fish response variables. All effects are mean-centered.
Appendix S8. Marginal spatial effect estimates for boosted generalized additive models for benthic macroinvertebrate response variables.
Appendix S9. Marginal spatial effect estimates for boosted generalized additive models for fish response variables.
Appendix S10. Correlation (Spearman) matrix of covariates.
Appendix S11. Fish diversity data file.
Appendix S12. Covariate data file.
As a service to our authors and readers, this journal provides supporting information supplied by the authors. Such materials may be re-organized for online delivery, but are not copy-edited or typeset. Technical support issues arising from supporting information (other than missing files) should be addressed to the authors.
|MEE3_124_sm_AppendixS1.doc||103K||Supporting info item|
|MEE3_124_sm_AppendixS10.csv||18K||Supporting info item|
|MEE3_124_sm_AppendixS2.jpg||1198K||Supporting info item|
|MEE3_124_sm_AppendixS3.doc||61K||Supporting info item|
|MEE3_124_sm_AppendixS4.doc||47K||Supporting info item|
|MEE3_124_sm_AppendixS5.doc||39K||Supporting info item|
|MEE3_124_sm_AppendixS6.pdf||3138K||Supporting info item|
|MEE3_124_sm_AppendixS7.doc||37K||Supporting info item|
|MEE3_124_sm_AppendixS8.jpg||355K||Supporting info item|
|MEE3_124_sm_AppendixS9.jpg||355K||Supporting info item|
|MEE3_124_sm_FishDiversity-richness.txt||67K||Supporting info item|
|MEE3_124_sm_MBSS-sites-USED-UPDATED-2.csv||797K||Supporting info item|
Please note: Wiley Blackwell is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.