USE AND INTERPRETATION OF LOGISTIC REGRESSION IN HABITAT-SELECTION STUDIES

By K. Keating, S. Cherry. 2004

595 citations recorded by the source corpus.

Subfields: Ecology, Small Animals, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/48abc6a2c81a8026c24346d6153d645e334551da

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Small Animals

In Statistics and Probability

Citations in the corpus

Variation in niche and distribution model performance: The need for a priori assessment of key causal factors (2012, background): “Much theory (Keating and Cherry, 2004; Pearce and Boyce, 2006; Phillips et al., 2009; Ward et al., 2009; Li et al., 2011) and data (Brotons et al.”
Climate change‐linked range expansion of Nathusius’ pipistrelle bat, Pipistrellus nathusii (Keyserling & Blasius, 1839) (2010, background): “This is an important distinction when interpreting models based on records that do not result from full surveys of all possible locations (Keating & Cherry, 2004).”
Protected areas network is not adequate to protect a critically endangered East Africa Chelonian: Modelling distribution of pancake tortoise, Malacochersus tornieri under current and future climates (2020, background): “Such models are commonly referred to as the resource selection functions in the habitat suitability literature (Manly et al. 2002, Keating and Cherry 2004, Johnson et al. 2006).”
Error and uncertainty in habitat models (2006, methodology): “The most statistically accurate way to model with pseudo-absence data is through the use of specialized models such as case control ( Keating & Cherry 2004; Pearce and Boyce 2006) and resource selection functions (Manly et al. 2002).”
Human Activity Differentially Redistributes Large Mammals in the Canadian Rockies National Parks (2011, methodology): “…the recommended method for evaluating resource selection because it appropriately measures availability from a mechanistically biological perspective (Moorcroft and Barnett 2008), and results in robust relative probabilities of selection in a used-availability design (Keating and Cherry 2004).”
Sample selection bias and presence-only distribution models: implications for background and pseudo-absence data. (2009, methodology): “We first investigate how to interpret models produced with random background, using the theory of use–availability sampling in habitat-selection studies (Keating and Cherry 2004).”
Niche and area of distribution modeling: a population ecology perspective (2010, methodology): “When unbiased absence data are available, correlative methods can be used to estimate the probability P (Y 1j ej ) of the species being present (Y 1), conditioned to environmental information e j (Guisan and Zimmermann 2000, Keating and Cherry 2004, Phillips et al. 2009).”
Study Designs and Tests for Comparing Resource Use and Availability II (2006, methodology): “For studies that used logistic regression, we identified the data type (see Keating and Cherry 2004) employed: single sample, case control (used–unused), use–availability, or paired use– availability.”
Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation (2008, background): “Perhaps more importantly, when used on presence-only data, regression-based methods suffer from the problem of ‘‘contaminated controls’’ (Keating and Cherry 2004), in Table 6.”
Accounting for animal movement in estimation of resource selection functions: sampling and data analysis. (2009, methodology): “For details on how we accounted for autocorrelation in the regression procedure and for the computation of robust standard errors of the selection coefficient estimates, see Appendix C.”
Accounting for spatially biased sampling effort in presence‐only species distribution modelling (2015, methodology): “Based on occurrence localities of rare (i.e. NatureServe S1- to S3-ranked; NatureServe, 2013) species of vascular plants, bryophytes and butterflies, the probability of sampling was estimated for each taxonomic group across Alberta using logistic regression (Keating & Cherry, 2004).”
Linking moose habitat selection to limiting factors (2005, unknown): “importance of habitat types (Keating and Cherry 2004).”
Modelling distribution and abundance with presence‐only data (2006, methodology): “Models estimated using case‐control logistic regression are based on the contrasts between used and control resource units and can be interpreted as odds ratios or relative likelihoods of occurrence ( Keating & Cherry 2004 ).”
Scale for resource selection functions (2006, methodology): “A special case of presence/absence is the case-control design where intensity of sampling of used and unused resource units is not random (Keating & Cherry, 2004).”
Resting structures and resting habitat of fishers in the southern Sierra Nevada, California (2009, methodology): “…by the unknown constant pr, and since we are interested only in the relationship between the response and the explanatory variables, we modeled logit(gi) as a linear regression model treating the intercept as a nuisance parameter (for more details see Manly et al., 1993; Keating and Cherry, 2004).”
Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines (2007, methodology): “Case-control regression that takes account of contaminated zeros is one example of this (Keating & Cherry, 2004; Pearce & Boyce, 2006), and relevant software for dealing with typical ecological applications is in development (Simon Barry, Gill Ward, pers.comm.).”