Using information theory as a substitute for stepwise regression in ecology and behavior

By G. Hegyi, L. Garamszegi. Behavioral Ecology and Sociobiology, 2010

182 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Evolution, Behavior and Systematics, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/c9c2730c311dba7a5bd95ab0eefb28888e304ee8

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

1. Roger Mundry
2. R. Freckleton
3. Mark J. Whittingham
4. S. Richards
5. Philip Stephens
6. Douglas H. Johnson
7. J. Fieberg
8. L. Garamszegi

In Ecology, Evolution, Behavior and Systematics

1. Roger Mundry
2. R. Freckleton
3. Mark J. Whittingham
4. Philip Stephens
5. S. Richards
6. G. Seress
7. A. Liker
8. T. Szép

In Nature and Landscape Conservation

1. Roger Mundry
2. Mark J. Whittingham
3. R. Freckleton
4. Philip Stephens
5. L. Garamszegi
6. S. Richards
7. Shinichi Nakagawa
8. J. Fieberg

Citations in the corpus

• Model selection and model averaging in behavioural ecology: the utility of the IT-AIC framework (2010, background): “The problems inherent to stepwise regression are well known in the statistical literature and have recently been explored in an ecological context (Whittingham et al. 2006; Hegyi and Garamszegi 2010).”
• Urbanization, nestling growth and reproductive success in a moderately declining house sparrow population (2012, methodology): “The inference yielded by the information-theoretic method depends critically on the set of candidate models chosen (Hegyi and Garamszegi 2011); how the potentially confounding variables interact to influence each dependent variable we measured is beyond both our knowledge and the scope of this study”
• MMI: Multimodel inference or models with management implications? (2015, background): “These and additional problems associated with allsubsets and stepwise selection are well known to statisticians, who agree that these methods should be abandoned (Burnham and Anderson 2002, Whittingham et al. 2006, Hegyi and Garamszegi 2011, Guidice et al. 2012).”
• Issues in information theory-based statistical inference—a commentary from a frequentist’s perspective (2010, methodology): “For strategies of obtaining a candidate set, see, e.g. Burnham et al. (2010) and Dochtermann and Jenkins (2010), and for more general discussions of this topic, see, e.g. Hegyi and Garamszegi (2010) or Symonds and Moussalli (2010).”
• A brief guide to model selection, multimodel inference and model averaging in behavioural ecology using Akaike’s information criterion (2010, unknown): “A traditional approach might seek to identify a ‘best model’ through forward or backward stepwise variate selection, a procedure whose shortcomings are well documented (Whittingham et al. 2006; but see Hegyi and Garamszegi 2010 ).”
• Dealing with collinearity in behavioural and ecological data: model averaging and the problems of measurement error (2010, methodology): “Hegyi and Garamszegi 2010 ) such suggestions are computational kludges, and ignore the wider problems (e.g.”