glmulti: An R Package for Easy Automated Model Selection with (Generalized) Linear Models

By V. Calcagno, C. Mazancourt. 2010

1,215 citations recorded by the source corpus.

We introduce glmulti, an R package for automated model selection and multi-model inference with glm and related functions. From a list of explanatory variables, the provided function glmulti builds all possible unique models involving these variables and, optionally, their pairwise interactions. Restrictions can be specified for candidate models, by excluding specific terms, enforcing marginality, or controlling model complexity. Models are fitted with standard R functions like glm. The n best models and their support (e.g., (Q)AIC, (Q)AICc, or BIC) are returned, allowing model selection and multi-model inference through standard R functions. The package is optimized for large candidate sets by avoiding memory limitation, facilitating parallelization and providing, in addition to exhaustive screening, a compiled genetic algorithm method. This article briefly presents the statistical framework and introduces the package, with applications to simulated and real data.

Subfields: Artificial Intelligence, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/24f6a684dd840e95df2875c23a8ca786dbfccae0

How researchers see this paper

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

In Artificial Intelligence

1. Wei-Wei Tu
2. Quanming Yao
3. Yang Yu
4. Qiang Yang
5. Yi-Qi Hu
6. Isabelle M Guyon
7. Hugo Jair Escalante
8. Yu-Feng Li

In Control and Systems Engineering

1. Kyle T. Martins
2. V. Arroyo‐Rodríguez
3. Yang Yu
4. Qiang Yang
5. M. Tabarelli
6. Hugo Jair Escalante
7. Isabelle M Guyon
8. Yu-Feng Li

Citations in the corpus

• Biodiversity inhibits parasites: Broad evidence for the dilution effect (2015, methodology): “We obtained the top 20 models (according to the corrected Akaike information criterion) from this set using a genetic algorithm implemented with the glmulti package in R (33).”
• Chronic anthropogenic disturbance drives the biological impoverishment of the Brazilian Caatinga vegetation (2015, methodology): “To correct for overdispersion associated with models with Poisson errors (Crawley 2007), we used QAICc values instead of AICc in such models (Calcagno & Mazancourt 2010).”
• Pollination services are mediated by bee functional diversity and landscape context (2015, methodology): “We screened all possible level two interactions of interest using an automated model selection program (‘glmulti’ package; Calcagno & Mazancourt 2010; Calgano 2012).”
• FWDselect : Variable selection algorithm in regression models (2013, neutral): “…to the criterion— and on the other hand, and more importantly , this method allows for better assessment of model-selection uncertainty and better performance of multi-model inference than a single model would (Burnham and Anderson, 2002; Johnson and Omland, 2004; Calcagno and de Mazancourt, 2010).”
• Sample size matters: investigating the effect of sample size on a logistic regression susceptibility model for debris flows (2014, neutral): “Recently, alternative approaches for model selection have been proposed (e.g.Calcagno and Mazancourt, 2010); they will be tested in future research.”
• Taking Human out of Learning Applications: A Survey on Automated Machine Learning (2018, background): “model selection classifiers selection of classifiers and their hyper-parameters [5], [34], [37], [48], [49]”