BranchGLM-package {BranchGLM} | R Documentation |
BranchGLM: Efficient Best Subset Selection for GLMs via Branch and Bound Algorithms
Description
Performs efficient and scalable glm best subset selection using a novel implementation of a branch and bound algorithm. To speed up the model fitting process, a range of optimization methods are implemented in 'RcppArmadillo'. Parallel computation is available using 'OpenMP'.
Author(s)
Maintainer: Jacob Seedorff jacob-seedorff@uiowa.edu
References
Seedorff J, Cavanaugh JE. Assessing Variable Importance for Best Subset Selection. Entropy. 2024; 26(9):801. doi:10.3390/e26090801
See Also
Useful links:
Report bugs at https://github.com/JacobSeedorff21/BranchGLM/issues
Examples
# Using iris data to demonstrate package usage
Data <- iris
# Fitting linear regression model
Fit <- BranchGLM(Sepal.Length ~ ., data = Data, family = "gaussian", link = "identity")
Fit
# Doing branch and bound best subset selection
VS <- VariableSelection(Fit, type = "branch and bound", metric = "BIC",
showprogress = FALSE, bestmodels = 10)
VS
## Plotting results
plot(VS, ptype = "variables")
[Package BranchGLM version 3.0.1 Index]