- press 'p' to see a note with a brief explanation for each slide
- press 'f' to see the presentation in 'full screen' mode
2015-09-10
what is validation?
criteria for SDM adequacy
suggestions for improvement
perhaps not a good term, better: evaluation (Oreskes, 1998)
- predictor variables - quality - resolution - realism - occurrence/abundance data - quality - size
- appropriate/balanced workflow - model-type/algorithm - training/testing cycle - error-metrics - quality checks/reproducibility
- choice of index/indices - splitting data for training & testing (evaluating) - avoiding artifacts & comparing across studies
- interpreting differences among models - deal with scale-effects - avoid over-interpretation of statistical relations