Constrain to perform: Regularization of habitat models

By B. Schr. 2006

79 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/01710a558ba4ded76b4454c2c12d1a4b4bead9e3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The virtual ecologist approach: simulating data and observers (2010, methodology): “Reineking and Schröder (2006) compared regularisation and variable selection methods for model calibration.”
Species Distribution Models: Ecological Explanation and Prediction Across Space and Time (2009, unknown): “Some methods focus on simultaneous selection of variables and parameter estimation, for example, by shrinking coefficient estimates (e.g., see Reineking & Schröder 2006 on ridge regression and the lasso).”
A working guide to boosted regression trees. (2008, methodology): “AND MODELLING All models were fitted in (R Development Core Team 2006) version 2.3-1, using gbm package version 1·5–7 (Ridgeway 2006) plus custom code written by J.L. and J.E.”
PresenceAbsence: An R Package for Presence Absence Analysis (2008, background): “It is the validation dataset from Moisen et al. (2006) , and more detailed information can be found in this paper.”
Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds (2012, background): “Spatial distribution models need to be well calibrated to be useful for predicting beyond the original spatial extent of input observations (Phillips and Elith, 2010; Reineking and Schröder, 2006).”
AUC: a misleading measure of the performance of predictive distribution models (2008, background): “…four different fractions in a two-by-two confusion matrix: the correctly predicted positive fraction or sensitivity; the correctly predicted negative fraction or specificity; the falsely predicted positive fraction (commission errors); and the falsely predicted negative fraction (omission errors).”
Estimation of suspended sediment concentration and yield using linear models, random forests and quantile regression forests (2008, methodology): “We selected the minimum adequate GLM by a stepwise-algorithm employing Bayes Information Criterion (BIC), which is stricter than the commonly used Akaike Information Criterion (AIC) (e.g. Reineking and Schröder, 2006).”
Assessing community-based conservation projects: A systematic review and multilevel analysis of attitudinal, behavioral, ecological, and economic outcomes (2013, unknown): “Some authors have suggested that stepwise regression can lead to biased estimates [93] and have suggested other approaches to model selection [94].”
Towards novel approaches to modelling biotic interactions in multispecies assemblages at large spatial extents (2012, methodology): “…for spatial processes (e.g. Banerjee et al., 2008), model selection procedures (Burnham & Anderson, 2002; O’Hara & Sillanpää, 2009), or shrinkage methods, which simultaneously estimate parameters whilst shrinking the unimportant ones towards zero (Tibshirani, 1996; Reineking & Schröder, 2006).”
Effects of incorporating spatial autocorrelation into the analysis of species distribution data (2007, background): “This is clearly a question deserving future research, since model predictions depend strongly on the bias introduced by the model structure ( Reineking & Schroder, 2006 ).”
Bunching up the background betters bias in species distribution models (2019, methodology): “In simulations, this alternative has been shown to outperform shrinkage methods when a minority of candidate predictors truly a ect the distribution and the sample size is su ciently large (Reineking and Schröder 2006).”