predict.BranchGLMVS: Predict Method for BranchGLMVS or summary.BranchGLMVS Objects

In BranchGLM: Efficient Best Subset Selection for GLMs via Branch and Bound Algorithms

Predict Method for BranchGLMVS or summary.BranchGLMVS Objects

Description

Obtains predictions from BranchGLMVS or summary.BranchGLMVS objects.

Usage

## S3 method for class 'BranchGLMVS'
predict(object, which = 1, ...)

## S3 method for class 'summary.BranchGLMVS'
predict(object, which = 1, ...)

Arguments

object	a BranchGLMVS or summary.BranchGLMVS object.
which	a positive integer to indicate which model to get predictions from, the default is 1 which is used for the best model. For the branch and bound algorithms the number k is used for the kth best model and for the stepwise algorithms the number k is used for the model that is k - 1 steps away from the final model.
...	further arguments passed to predict.BranchGLM.

Value

A numeric vector of predictions.

See Also

predict.BranchGLM

Examples

Data <- iris
Fit <- BranchGLM(Sepal.Length ~ ., data = Data, 
family = "gamma", link = "log")

# Doing branch and bound selection 
VS <- VariableSelection(Fit, type = "branch and bound", metric = "BIC", 
bestmodels = 10, showprogress = FALSE)

## Getting predictions from best model
predict(VS, which = 1)

## Getting linear predictors from 5th best model
predict(VS, which = 5, type = "linpreds")

BranchGLM documentation built on Sept. 28, 2024, 9:07 a.m.