COMPARISON OF STATISTICAL APPROACHES FOR MODELING FISH SPECIES DISTRIBUTIONS

By Julian D. Olden, Donald A. Jackson. 2002

228 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/457bdf94500128588a6cd89639a426248988dd8e

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

Habitat suitability for marine fishes using presence-only modelling and multibeam sonar (2010, background): “…the same data, and the majority of these have focused on terrestrial, freshwater or simulated datasets (Elith & Burgman 2002, Ferrier et al. 2002b, Olden & Jackson 2002, Farber & Kadmon 2003, Loiselle et al. 2003, Brotons et al. 2004, Segurado & Araújo 2004, Elith et al. 2006, Tsoar et al. 2007).”
Multiscale effects of flow regime and habitat and their interaction on fish assemblage structure in eastern Australia (2007, background): “Neural networks have been shown to exhibit substantially higher predictive power (based on empirical and simulated data) when modelling nonlinear relationships compared with logistic regression, linear discriminant analysis, or classification trees (Olden and Jackson 2002).”
The effect of species response form on species distribution model prediction and inference (2009, background): “It has also been posed by Olden and Jackson (2002).”
Species-specific traits associated to prediction errors in bird habitat suitability modelling (2005, methodology): “These techniques have been compared in terms of predictive accuracy and ease of use (Guisan et al., 1999; Manel et al., 1999; Olden and Jackson, 2002; Segurado and Araújo, 2004; Yen et al., 2004), with the conclusion that there is not a single best method.”
Machine Learning Methods Without Tears: A Primer for Ecologists (2008, methodology): “In reference to a back-propagation feedforward approach, ANNs have a number of advantages over traditional parametric approaches, including: (1) the ability to model nonlinear associations; (2) no requirement of specific assumptions concerning the distributional characteristics of the independent va”
Impacts of climate change on the seasonal distribution of migratory caribou (2009, methodology): “Instead of designating caribou presence by the traditional decision threshold of 0.50, we constructed Receiver Operating Curves (ROC) to identify the threshold that would maximize species sensitivity and specificity (Fielding & Bell, 1997; Olden & Jackson, 2002).”
Decadal diet shift in yellowfin tuna Thunnus albacares suggests broad-scale food web changes in the eastern tropical Pacific Ocean (2014, background): “…approach developed by Breiman et al. (1984), has provided insight into the interpretation of a variety of complex ecological data (e.g. Olden & Jackson 2002, Zuur et al. 2007, Massey et al. 2008, Davidson et al. 2009), including foraging ecology (Iverson et al. 1997, Smith et al.…”
Modelling stream fish species distribution in a river network: the relative effects of temperature versus physical factors (2008, background): “…in modelling species responses and it has already been shown that modelling techniques able to summarise non-linear and complex relationships have greater efficiency than linear approaches (Brosse & Lek 2000; Bio et al. 2002; Olden & Jackson 2002; Segurado & Araujo 2004; Araujo et al. 2005).”
An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data (2004, methodology): “Illustration of the critical difference between the Connection Weight Approach (Olden and Jackson, 2002b) and Garson's Algorithm (Garson, 1991) that results in their differential ability to correctly identify variable importance in neural networks.”
Assessing the Habitat Requirements of Stream Fishes: An Overview and Evaluation of Different Approaches (2003, methodology): “…regression and discriminant function analysis are commonly used for modeling species presence, classification trees and artificial neural networks are alternative nonlinear approaches that may provide more robust models of species distribution (Guisan and Zimmermann 2000; Olden and Jackson 2002).”