A new null model approach to quantify performance and significance for ecological niche models of species distributions

Aim Ecological niche modelling requires robust estimation of model performance and significance, but common evaluation approaches often yield biased estimates. Null models provide a solution but are rarely used in this field. We implemented an important modification to existing null model tests, evaluating null models with the same withheld records that were used to evaluate the real model. We built and evaluated models across a range of modelling scenarios and for various performance measures using the algorithm Maxent and the monk parakeet (Myiopsitta monachus). Location Native range in Southern America and global invasions predominantly in North/Central America and Europe. Methods We tested the ability of models built under 15 scenarios (five sets of calibration records and three settings that varied the level of model complexity) to predict spatially independent evaluation data in the invaded range (in effect, testing the models under spatial transfer). We quantified performance with measures of discriminatory ability and overfitting based on area under the receiver operating characteristic curve (AUC) and the omission error rate. We estimated null distributions of these measures and calculated effect size and significance. We determined how these estimates varied across modelling scenarios, comparing with two tests existing in the literature. Results Performance varied starkly across modelling scenarios. As expected, the measures of overfitting agreed with each other and provided different information than that of discriminatory ability. However, high performance per se did not show strong association with high effect size and significance. Main Conclusions Ecological niche models should be assessed with measures of effect size and significance based on appropriate null distributions, in contrast to several approaches existing in the literature. The proposed approach using independent evaluation data, implemented with our accompanying code and R package, allows such estimates for either the same or a different region/time period, and it merits use and continued development.