Abstract
BackgroundMultiple logistic regression is precluded from many practical applications in ecology that aim to predict the geographic distributions of species because it requires absence data, which are rarely available or are unreliable. In order to use multiple logistic regression, many studies have simulated "pseudo-absences" through a number of strategies, but it is unknown how the choice of strategy influences models and their geographic predictions of species. In this paper we evaluate the effect of several prevailing pseudo-absence strategies on the predictions of the geographic distribution of a virtual species whose "true" distribution and relationship to three environmental predictors was predefined. We evaluated the effect of using a) real absences b) pseudo-absences selected randomly from the background and c) two-step approaches: pseudo-absences selected from low suitability areas predicted by either Ecological Niche Factor Analysis: (ENFA) or BIOCLIM. We compared how the choice of pseudo-absence strategy affected model fit, predictive power, and information-theoretic model selection results.ResultsModels built with true absences had the best predictive power, best discriminatory power, and the "true" model (the one that contained the correct predictors) was supported by the data according to AIC, as expected. Models based on random pseudo-absences had among the lowest fit, but yielded the second highest AUC value (0.97), and the "true" model was also supported by the data. Models based on two-step approaches had intermediate fit, the lowest predictive power, and the "true" model was not supported by the data.ConclusionIf ecologists wish to build parsimonious GLM models that will allow them to make robust predictions, a reasonable approach is to use a large number of randomly selected pseudo-absences, and perform model selection based on an information theoretic approach. However, the resulting models can be expected to have limited fit.
Highlights
Multiple logistic regression is precluded from many practical applications in ecology that aim to predict the geographic distributions of species because it requires absence data, which are rarely available or are unreliable
If ecologists wish to build parsimonious Generalised Additive Model (GLM) models that will allow them to make robust predictions, a reasonable approach is to use a large number of randomly selected pseudoabsences, and perform model selection based on an information theoretic approach
Model predictive power Area Under the Curve (AUC) for predictions resulting from one-step profile methods (BIOCLIM and Ecological Niche Factor Analysis (ENFA)), were lower than those obtained from logistic regression models (LRM)
Summary
Multiple logistic regression is precluded from many practical applications in ecology that aim to predict the geographic distributions of species because it requires absence data, which are rarely available or are unreliable. BMC Ecology 2009, 9:8 http://www.biomedcentral.com/1472-6785/9/8 change or biological invasions These tools relate field observations to environmental predictor variables, based on statistically or theoretically derived response surfaces, for prediction and inference [1]. Examples of profile techniques include BIOCLIM [5], DOMAIN [6], Species-PCA [4], and Ecological Niche Factor Analysis: ENFA [7] Their development and use has been stimulated by the many presence-only data available in existing natural history collections [8]. Group discrimination techniques are derived from established statistical approaches and are more numerous than profile techniques They include classical regression-based approaches such as generalised linear and additive models [9,10] and more recent and robust techniques such as boosted regression trees (e.g. BRT; [11] or random forest:RF [12]). See [13] and [1] for a more exhaustive overview of existing approaches
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
