Deciphering ecology from statistical artefacts: Competing influence of sample size, prevalence and habitat specialization on species distribution models and how small evaluation datasets can inflate metrics of performance

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.

• Publication year

  2020

• Venue

  Diversity and Distributions: A journal of biological invasions and biodiversity

• Publication date

  2020-01-09

• Fields of study

  Biology, Mathematics, Environmental Science

• Identifiers
  DOI 10.1111/ddi.13030
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Effects of grain size and niche breadth on species distribution modeling

  2018cited by this paper
• Effects of simulated observation errors on the performance of species distribution models

  2018cited by this paper
• Temperature and hydrologic alteration predict the spread of invasive Largemouth Bass (Micropterus salmoides).

  2018cited by this paper
• Niche centrality and human influence predict rangewide variation in population abundance of a widespread mammal: The collared peccary (Pecari tajacu)

  2018cited by this paper
• Sensitivity of fine‐scale species distribution models to locational uncertainty in occurrence data across multiple sample sizes

  2017cited by this paper
• Effects of species prevalence on the performance of predictive models

  2017cited by this paper
• The interplay of various sources of noise on reliability of species distribution models hinges on ecological specialisation

  2017cited by this paper
• Invasive potential of the pied crow (Corvus albus) in eastern Brazil: best to eradicate before it spreads

  2017cited by this paper
• Modeling / GIS , Risk Assessment , Economic Impact Characterizing environmental suitability of Aedes albopictus ( Diptera : Culicidae ) in Mexico based on regional and global niche models

  2017cited by this paper
• Habitat Selection by Burrowing Owls Athene cunicularia in the Pampas of Argentina: A Multiple-Scale Assessment

  2016cited by this paper
• Minimum required number of specimen records to develop accurate species distribution models

  2016influential reference
• The effects of model and data complexity on predictions from species distributions models

  2016cited by this paper
• Ecological niche variation in the Wilson's warbler Cardellina pusilla complex

  2015cited by this paper
• Uncertainty in ensemble modelling of large-scale species distribution: Effects from species characteristics and model techniques

  2015influential reference
• Abundance models improve spatial and temporal prioritization of conservation resources.

  2015influential reference
• Precipitation and winter temperature predict long‐term range‐scale abundance changes in Western North American birds

  2014cited by this paper
• Species distribution modelling for the people: unclassified landsat TM imagery predicts bird occurrence at fine resolutions

  2013cited by this paper
• Species distribution models in conservation biogeography: developments and challenges

  2013cited by this paper
• Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling

  2012cited by this paper
• Incorporating uncertainty in predictive species distribution modelling

  2012cited by this paper
• Uses and misuses of bioclimatic envelope modeling.

  2012cited by this paper
• The effects of small sample size and sample bias on threshold selection and accuracy assessment of species distribution models

  2012influential reference
• The effect of a gradual response to the environment on species distribution modeling performance

  2012cited by this paper
• Defining and measuring ecological specialization

  2010cited by this paper
• Do they? How do they? WHY do they differ? On finding reasons for differing performances of species distribution models

  2009cited by this paper
• Is bird incidence in Atlantic forest fragments influenced by landscape patterns at multiple scales?

  2009cited by this paper
• eBird: A citizen-based bird observation network in the biological sciences

  2009cited by this paper
• The effect of prevalence and its interaction with sample size on the reliability of species distribution models

  2009cited by this paper
• Not as good as they seem: the importance of concepts in species distribution modelling

  2008cited by this paper
• Rethinking receiver operating characteristic analysis applications in ecological niche modeling

  2008cited by this paper
• Effects of sample size on the performance of species distribution models

  2008influential reference
• AUC: a misleading measure of the performance of predictive distribution models

  2008cited by this paper
• A working guide to boosted regression trees.

  2008cited by this paper
• Effects of species’ ecology on the accuracy of distribution models

  2007influential reference
• Sensitivity of predictive species distribution models to change in grain size

  2007cited by this paper
• A comparative evaluation of presence‐only methods for modelling species distribution

  2007cited by this paper
• The effect of sample size and species characteristics on performance of different species distribution modeling methods

  2006cited by this paper
• Uncertainty of bioclimate envelope models based on the geographical distribution of species

  2005cited by this paper
• Would climate change drive species out of reserves? An assessment of existing reserve‐selection methods

  2004cited by this paper
• Protected Areas and Climate Change: a Case Study of the Cacti in the Tehuacán‐Cuicatlán Biosphere Reserve, México

  2003cited by this paper
• Effects of sample size on accuracy of species distribution models

  2002influential reference
• Evaluating the predictive performance of habitat models developed using logistic regression

  2000cited by this paper
• Niche Breadth, Resource Availability, and Inference

  1982influential reference

• Species distribution model performance improves when habitat characterizations are centered on detected individuals instead of observers

  2025cites this paper
• Inhibition of Photosynthesis in Quercus acutissima Seedlings by LaCl3 Through Calcium Signaling Regulation

  2025cites this paper
• Too few, too many, or just right? Optimizing sample sizes for population-level inferences in animal tracking projects

  2025cites this paper
• Coupling ensemble of small models with UAV-derived structural and textural metrics to predict occurrence of an invasive alien plant in an urban woodland reserve

  2025cites this paper
• Spatial Modeling of Yellowfin Tuna in the Banda Sea Based on Oceanographic Factors Using MaxEnt

  2025cites this paper
• Projected Impacts of Climate and Land Use Change on Endemic Plant Distributions in a Mediterranean Island Hotspot: The Case of Evvia (Aegean, Greece)

  2025cites this paper
• The time of acquisition of multispectral predictors matters: the role of seasonality in bird species distribution models

  2025cites this paper
• Testing spatial transferability of species distribution models reveals differing habitat preferences for an endangered delphinid (Cephalorhynchus hectori) in Aotearoa, New Zealand

  2024cites this paper
• Optimising occurrence data in species distribution models: sample size, positional uncertainty, and sampling bias matter

  2024cites this paper
• A retrospective approach for evaluating ecological niche modeling transferability over time: the case of Mexican endemic rodents

  2024cites this paper
• The role of ecological niche conservatism in the evolution of bird distributional patterns in Mesoamerican seasonally dry forests

  2024cites this paper
• Ensemble forecasting of Persian leopard (Panthera pardus saxicolor) distribution and habitat suitability in south-western Iran

  2024cites this paper
• Corythauma ayyari (Insecta, Heteroptera, Tingidae) depends on its host plant to spread in Europe

  2024cites this paper
• No optimal spatial filtering distance for mitigating sampling bias in ecological niche models

  2024cites this paper
• Supplemental structured surveys and pre-existing detection models improve fine-scale density and population estimation with opportunistic community science data

  2024influential citation
• Can we accurately predict the distribution of soil microorganism presence and relative abundance?

  2024cites this paper
• Causal inference and large‐scale expert validation shed light on the drivers of SDM accuracy and variance

  2023cites this paper
• SDM profiling: A tool for assessing the information-content of sampled and unsampled locations for species distribution models

  2023cites this paper
• Exploring Old Data with New Tricks: Long-Term Monitoring Indicates Spatial and Temporal Changes in Populations of Sympatric Prairie Grouse in the Nebraska Sandhills

  2023cites this paper
• Ensemble modelling under multiple climate change scenarios predicts reduction in highly suitable range of habitats of Dactylorhiza hatagirea (D.Don) Soo in Himachal Pradesh, western Himalaya

  2023cites this paper
• Small to train, small to test: Dealing with low sample size in model evaluation

  2023cites this paper
• Distributions of two native ungulates at the third pole are highly sensitive to global warming

  2022cites this paper
• Positional errors in species distribution modelling are not overcome by the coarser grains of analysis

  2022cites this paper
• A comparison of remotely sensed environmental predictors for avian distributions

  2022cites this paper
• Grand challenges at the frontiers of bird science

  2022cites this paper
• Predicting the potential distribution of the invasive freshwater diatom Lindavia intermedia in New Zealand lakes

  2021cites this paper
• The uniform AUC: Dealing with the representativeness effect in presence–absence models

  2021cites this paper
• Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage

  2021cites this paper
• Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage

  2021cites this paper
• Species distribution modelling sheds light on the widespread distribution of Sphingonotus (Sphingonotus) rubescens (Orthoptera: Acrididae: Oedipodinae)

  2021cites this paper
• A data-integration approach to correct sampling bias in species distribution models using multiple datasets of breeding birds in the Swiss Alps

  2021cites this paper
• Comparing multi- and single-scale species distribution and abundance models built with the boosted regression tree algorithm

  2020cites this paper
• Bioclimatic modeling of potential vegetation types as an alternative to species distribution models for projecting plant species shifts under changing climates

  2020cites this paper
• Building a better baseline to estimate 160 years of avian population change and create historically informed conservation targets

  2020cites this paper
• BENCHMARKING THE AVIAN DIVERSITY OF OREGON IN AN ERA OF RAPID CHANGE

  2020cites this paper
• Climate change increases the distribution of reservoirs of the Raccoon Rabies Virus in Quebec

  year unknowncites this paper