Aim: Sample size and species characteristics, including prevalence and habitat specialization, can influence the predictive performance of species distribution models (SDMs). There is little agreement, however, on which metric of model performance to use. Here, we directly compare AUC and partial ROC as metrics of SDM performance through analyses on the effects of species traits and sample size on SDM performance.Location: Three counties dominated by agricultural lands and coniferous forest in Oregon's Willamette Valley and Coast Range ecoregions.Methods: We systematically reduced a large avian point count dataset to alter sample sizes of 22 species of songbird. We used boosted regression trees to run SDMs for each species, quantified habitat specialization, and used mixed effects models to compare the influence of sample size, prevalence, and habitat specialization on SDM performance, calculated as AUC and partial ROC, across species. We calculated AUC and partial ROC with subset and independent evaluation data separately to more comprehensively investigate differences in metrics.Results: We found a positive quadratic effect of sample size and a strongly positive effect of habitat specialization on both metrics of model performance. We found a weak effect of prevalence on partial ROC and no effect in AUC. Contrary to expectations, when evaluated with a subset evaluation data, partial ROC was consistently highest in models with the smallest sample sizes. These small sample size models had correspondingly small sample sizes in subset evaluation datasets. Partial ROC evaluated with independent data and AUC evaluated with subset or independent data showed the expected positive correlation between sample size and model performance.Main Conclusions: We found that small evaluation datasets can artificially inflate partial ROC. With literature recommended minimum SDM sample sizes as low as three, attention must be given to the effects of correspondingly low sample sizes in evaluation datasets.

Global change in climate and land use has profound effects on species' geographic and elevational distributions. In European birds, while species are predicted to track their climatic niches upslope, lowland agricultural intensification and high‐elevation land abandonment can drive elevational shifts. Species traits that can predict response to change in climate and land use can inform conservation, but a thorough examination of their relationships with elevational shifts in European birds is lacking. We estimate the change in the elevational distributions of 71 species from 1996 to 2016 in a region of the western Palearctic with wide elevational gradients (approximately 3000 m) and large changes in temperature. We model the relationships between elevational shifts and species traits associated with resource preference and adaptive capacity at five reference points including the cool edge, warm edge, and the core of species' elevational distributions. When intermediate reference points were removed, changes to the results were negligible, indicating that three reference points are likely sufficient. We found significant upslope and downslope shifts in 56% and 23% of our study species, respectively. Asymmetric rates of shifts in the cool and warm edges caused significant contractions in elevational extent in 30% of our study species. The effect of elevational preference (i.e., midpoint elevation) was habitat dependent. Movement in alpine birds was unidirectionally upslope, with nearly half displaying significant or apparent elevational range contractions. In woodland birds, asymmetries of shifts in reference points led to expansions in extent in low‐elevation species and contractions in high‐elevation species. Generally, migrants, species with smaller mass, smaller relative brain size, smaller hand‐wing index, and generalists in diet, habitat, and elevation had greater upslope shifts. While elevational shifts in European birds were heterogenous and species‐specific, many were rapid, and species traits associated with resource preference and adaptive capacity were associated with common patterns of elevation.