Skip to contents

Computes normal-approximation confidence intervals for pseudo-weighted means or category prevalence returned by pwmean.

Usage

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

Arguments

object

An object of class "pwmean" or "pwmean_factor" returned by pwmean.

parm

A character vector of estimate names, as returned by names(coef(object)), or a numeric vector of positive integer positions. If omitted, all estimates are included.

level

A single numeric confidence level strictly between 0 and 1. Defaults to 0.95.

...

Additional arguments, currently unused.

Value

A numeric matrix with one row per requested estimate and two columns containing the lower and upper confidence limits. Column names give the corresponding tail probabilities as percentages. Selecting one estimate still returns a matrix.

Details

Intervals use the pseudo-weighted estimates and standard errors stored in object$estimates, with standard normal critical values. At the default confidence level, the intervals match the stored adjusted_lower and adjusted_upper columns.

Row names match names(coef(object)). Objects of class "pwmean_factor" inherit this method. Intervals for category prevalence are not truncated to the range from 0 to 1, consistent with the intervals stored by pwmean().