Compute confidence intervals for risks — confint.absRiskCB • casebase

This function uses parametric bootstrap to compute confidence intervals for the risk estimates. Since it relies on MLE theory for the validity of these intervals, this function only works for fit_obj that was fitted using family = "glm" (i.e. the default).

# S3 method for class 'absRiskCB'
confint(object, parm, level = 0.95, nboot = 500, ...)

Arguments

object: Output of function absoluteRisk.
parm: Output of function fitSmoothHazard that was used to compute object.
level: The confidence level required.
nboot: The number of bootstrap samples to use.
...: Additional arguments for methods.

Value

If there is only one covariate profile, the function returns a matrix with the time points, the risk estimates, and the confidence intervals. If there are more than one covariate profile, the function returns a list with three components.

Details

If the package progress is available, the function also reports on progress of the sampling (which can take some time if there are many covariate profiles and/or time points).