sigma.BranchGLM: Extract Square Root of the Dispersion Parameter Estimates

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

Extract Square Root of the Dispersion Parameter Estimates

Description

Extracts the square root of the dispersion parameter estimates from BranchGLM objects.

Usage

## S3 method for class 'BranchGLM'
sigma(object, ...)

Arguments

object	a BranchGLM object.
...	further arguments passed to or from other methods.

Value

A numeric vector of length 2 with first and second elements giving

mle	the MLE of the dispersion parameter
pearson	the Pearson estimator of the dispersion parameter

Note

The dispersion parameter for binomial and Poisson regression is always fixed to be 1. The MLE of the dispersion parameter is used in the calculation of the log-likelihood while the Pearson estimator of the dispersion parameter is used to calculate standard errors for the coefficient estimates.

Examples

Data <- iris
Fit <- BranchGLM(Sepal.Length ~ ., data = Data, family = "gaussian", link = "identity")
sigma(Fit)

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