Journal article
POC plots: Calibrating species distribution models with presence-only data
SJ Phillips, J Elith
Ecology | Published : 2010
DOI: 10.1890/09-0760.1
Abstract
Statistical models are widely used for predicting species' geographic distributions and for analyzing species' responses to climatic and other predictor variables. Their predictive performance can be characterized in two complementary ways: discrimination, the ability to distinguish between occupied and unoccupied sites, and calibration, the extent to which a model correctly predicts conditional probability of presence. The most common measures of model performance, such as the area under the receiver operating characteristic curve (AUC), measure only discrimination. In contrast, we introduce a new tool for measuring model calibration: the presence-only calibration plot, or POC plot. This to..
View full abstractGrants
Awarded by ARC
Awarded by Australian Research Council
Funding Acknowledgements
We thank Simon Ferrier and Miro Dudik for helpful comments and suggestions. Jane Elith was funded by ARC grant DP0772671 and the Australian Centre of Excellence for Risk Analysis. The data used in the case study would not have been compiled if not for the funding of the National Centre of Ecological Analysis and Synthesis, Santa Barbara, California, USA, and the initiative of Craig Moritz and Town Peterson. We are grateful to the custodians of the data for permission to use it: A. Ford, CSIRO Atherton, and Steven Williams, JCU Townsville, for AWT data; M. Peck and G. Peck, Royal Ontario Museum, and M. Cadman, Bird Studies Canada, Canadian Wildlife Service of Environment Canada, for CAN data; the National Vegetation Survey Databank and the Allan Herbarium, for NZ data; Missouri Botanical Garden, especially R. Magill and T. Consiglio, for SA data; and T. Wohlgemuth and U. Braendi from WSL Switzerland for SWI data.