glmulti is an R package for automated model selection and model-averaging, authored by Vincent Calcagno. It provides a wrapper for glm and other functions, generating all possible models under user constraints and finding the best models using Information Criteria like AIC, AICc, or BIC. The package can handle very large numbers of candidate models and includes a Genetic Algorithm for non-exhaustive searches.
Use Cases
- Automated selection of the best statistical model based on AIC, AICc, or BIC criteria.
- Model-averaging for inference when multiple candidate models perform similarly.
- Efficiently exploring large model spaces using a built-in Genetic Algorithm.
- Comparing and ranking candidate models generated from a set of explanatory variables.
Strengths
- Designed to handle very large numbers of candidate models.
- Includes a Genetic Algorithm for efficient search when exhaustive screening is infeasible.
- Supports multiple Information Criteria (AIC, AICc, BIC) for model comparison.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
Provenance
- Source
- Vincent Calcagno
- Collection Method
- Likely developed as an open-source R package for statistical computing.
- Time Range
- null
- Freshness
- Last update date is unknown; freshness unverified.
- Geography
- null