confint.BranchGLM {BranchGLM} | R Documentation |
Finds profile likelihood ratio confidence intervals for beta coefficients with the ability to calculate the intervals in parallel.
## S3 method for class 'BranchGLM'
confint(object, parm, level = 0.95, parallel = FALSE, nthreads = 8, ...)
object |
a |
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 |
a logical value to indicate if parallelization should be used. |
nthreads |
a positive integer to denote the number of threads used with OpenMP,
only used if |
... |
further arguments passed from other methods. |
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.
An object of class BranchGLMCIs
which is a list with the following components.
CIs |
a numeric matrix with the confidence intervals |
level |
the supplied level |
MLE |
a numeric vector of the MLEs of the coefficients |
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)