confint.BranchGLM: Likelihood Ratio Confidence Intervals for Beta Coefficients

In BranchGLM: Efficient Branch and Bound Variable Selection for GLMs using 'RcppArmadillo'

Likelihood Ratio Confidence Intervals for Beta Coefficients

Description

Likelihood Ratio Confidence Intervals for Beta Coefficients

Usage

## S3 method for class 'BranchGLM'
confint(object, parm, level = 0.95, parallel = FALSE, nthreads = 8, ...)

Arguments

object	a BranchGLM object.
parm	a specification of which parameters are to be given confidence intervals, either a vector of numbers or a vector of names. If missing, all parameters are considered.
level	the confidence level required.
parallel	whether or not to make use of parallelization via OpenMP.
nthreads	number of threads used with OpenMP, only used if parallel = TRUE.
...	further arguments passed from other methods.

Details

Endpoints of the confidence intervals that couldn't be found by the algorithm are filled in with NA. When there is a lot of multicollinearity in the data the algorithm may have problems finding many of the intervals.

Value

An object of class BranchGLMCIs which is a list with the following components.

CIs	a matrix with the confidence intervals
level	the supplied level
MLE	a numeric vector of the MLEs of the coefficients

Examples

Data <- iris
### Fitting linear regression model
mymodel <- BranchGLM(Sepal.Length ~ ., data = Data, family = "gaussian", link = "identity")

### Getting confidence intervals
CIs <- confint(mymodel, level = 0.95)
CIs

### Plotting CIs
plot(CIs, mary = 7, cex.y = 0.9)

BranchGLM documentation built on Aug. 31, 2023, 5:17 p.m.