Model selection and information theory in geographical ecology

By J. Diniz-Filho, Thiago Fernando Rangel, Luis Mauricio Bini. 2008

218 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/28c6b6022a46834848821dbc4a641db1d2cd3d5e

How researchers see this paper

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

In Ecological Modeling

In Ecology

In Nature and Landscape Conservation

Citations in the corpus

Understanding what controls the spatial distribution of fish populations using a multi-model approach (2011, methodology): “…in the data will tend to generate longer (with more explanatory variables) models, so that the problem is analogous to the inflated Type I errors in the NHST approach, which tend to give more statistical importance to some explanatory variables than they really have (Diniz-Filho et al., 2008).”
Historical climate‐change influences modularity and nestedness of pollination networks (2013, methodology): “…modularity M decreases linearly with increasing historical climate-change or only decreases at high historical climate-change values, for each of the four historical climate predictors we conducted the model selection analyses based on information theory outlined in Diniz-Filho et al. (2008).”
Accounting for uncertainty when mapping species distributions: The need for maps of ignorance (2011, unknown): “The best predictors can be discarded or not accounted for in either manual or automated model selection processes (see, for example, Diniz-Filho et al., 2008; Fattorini, 2005; Ginzburg et al., 2007; Heikkinen et al., 2006; Maggini et al., 2006).”
Predation has a greater impact in less productive environments: variation in roe deer, Capreolus capreolus, population density across Europe (2009, background): “Diniz-Filho et al. (2008) stressed that the AIC is sensitive to the presence of spatial autocorrelation and may generate unstable and overfitted minimum adequate models to describe macroecological data.”
The macroecology of phylogenetically structured hummingbird–plant networks (2015, methodology): “MAMs were defined as models exhibiting a difference in AICC of at least two points lower than other models (i.e. ΔAICC < 2; Burnham & Anderson, 2002; Diniz-Filho et al., 2008).”
Macroecological trends in nestedness and modularity of seed-dispersal networks: human impact matters (2015, methodology): “We did this by calculating the linear combination of the detected spatial filters, and using it as a covariable in an ordinary least-square framework (Diniz-Filho et al., 2008).”
Eight (and a half) deadly sins of spatial analysis (2012, methodology): “One can use model averaging, which does have real advantages (Burnham & Anderson, 2002; Diniz-Filho et al., 2008), but this does not resolve the issue of whether the particular methods being used are even valid, which brings us to the problem of uncritical uses of multiple regression.”
Habitat selection of breeding riparian birds in an urban environment: untangling the relative importance of biophysical elements and spatial scale (2011, background): “…candidate models that included a ‘fixed’ spatial explanatory variable taken from a pure autoregressive model (ARM) in order to account for the Diversity and Distributions, 17, 506–518, ª 2011 Blackwell Publishing Ltd 509 spatial autocorrelation in the residuals (see Diniz-Filho et al., 2008).”