Spatial predictive models have been increasingly employed to generate spatial predictions for environmental management and conservation in parallel to the advancement in data acquisition, data processing and computing capabilities. The accuracy of predictive models and their predictions is crucial to evidence-informed decision making and policy. However, the accuracy of predictive models in general is unknown and often accessed using error measures or even correlation measure. In this study, we clarified relevant issues about variance explained for predictive models (VEcv), established the relationships between commonly used predictive error measures like root mean square error (RMSE) and VEcv, unified these measures under VEcv, discovered that VEcv is independent of unit/scale and data variation, quantified the relationships between these error measures and data variation, and quantified the relationship between relative root mean square error (RRMSE) and relative mean absolute error (RMAE). We then assessed the performance of predictive models in the environmental sciences based on about 300 previously published applications and then classified the predictive models based on their performance. This study provided a tool to directly compare the accuracy of predictive models for data with different unit/scale and variation, and established a cross-disciplinary context and benchmark for assessing predictive models in environmental sciences and other disciplines. Recommendations for future studies were provided to objectively assess the performance of predictive models and make the accuracy of predictive models for different disciplines directly comparable.
Abstract presented at the 23rd Australian Statistical Conference 2016
