Multi-Model Inference
Second-order Akaike Information Criterion
Adaptive Regression by Mixing
Apply a function to calls inside an expression
Bates-Granger minimal variance model weights
Bootstrap model weights
Plot model coefficients
Cos-squared model weights
Flour beetle mortality data
Cement hardening data
Grade Point Average data
Automated model selection
Retrieve models from selection table
Various information criteria
Jackknifed model weights
Leave-one-out cross-validation
Manipulate model formulas
Combine model selection tables
Model utility functions
Model averaging
model selection table
Description of Model Selection Objects
Multi-model inference
Identify nested models
Parameter averaging
Automated model selection using parallel computation
Visualize model selection table
Predict method for averaged models
Quasi AIC or AICc
QIC and quasi-Likelihood for GEE
Pseudo-R-squared for Generalized Mixed-Effect models
Likelihood-ratio based pseudo-R-squared
Stacking model weights
Standardized model coefficients
Standardize data
Subsetting model selection table
Per-variable sum of model weights
List of supported models
Make a function return updateable result
Akaike weights
Tools for model selection and model averaging with support for a wide range of statistical models. Automated model selection through subsets of the maximum model, with optional constraints for model inclusion. Averaging of model parameters and predictions based on model weights derived from information criteria (AICc and alike) or custom model weighting schemes.