Logistic regression models for predicting occurrence of terrestrial molluscs in southern Sweden – importance of environmental data quality and model complexity

By Åke Berg, U. Gärdenfors, T. Proschwitz. 2004

46 citations recorded by the source corpus.

How researchers see this paper

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

Uncertainty associated with survey design in Species Distribution Models (2014, background): “Many studies have highlighted that geographical and ecological species’ characteristics affect SDM accuracy (Berg et al., 2004; Segurado & Ara ujo, 2004; Guisan et al., 2007).”
Threshold criteria for conversion of probability of species presence to either–or presence–absence (2007, methodology): “…are actually widely used in order to generate binary distribution maps (see, for example, Li et al., 1997; Guisan et al., 1998; Manel et al., 1999a; Fleishman et al., 2001; Thuiller, 2003; Berg et al., 2004; Meggs et al., 2004; Segurado and Araújo, 2004; Araújo et al., 2005; Luoto et al., 2005).”
A comparative evaluation of presence‐only methods for modelling species distribution (2007, background): “Similar results were reported in studies comparing other modelling techniques (e.g. Manel et al ., 1999; Elith & Burgman, 2002; Thuiller et al ., 2003; Berg et al ., 2004).”
The ghost of unbalanced species distribution data in geographical model predictions (2006, background): “The intuitively appealing 0.5 cut-off (e.g. Li et al ., 1997; Berg et al ., 2004; Meggs et al ., 2004) makes no sense, as each model has its own characteristics related to prevalence and fit.”