confidence_multinomial {arkhe}

Confidence Interval for Multinomial Proportions

Description

Computes a Wald interval for a proportion at a desired level of significance.

Usage

confidence_multinomial(object, ...)

## S4 method for signature 'numeric'
confidence_multinomial(
  object,
  level = 0.95,
  method = "wald",
  corrected = FALSE
)

Arguments

object

A numeric vector of positive integers giving the number of occurrences of each class.

...

Currently not used.

level

A length-one numeric vector giving the confidence level. Must be a single number between 0 and 1.

method

A character string specifying the method to be used. Any unambiguous substring can be used.

corrected

A logical scalar: should continuity correction be used? Only used if method is "wald".

Value

A two column numeric matrix giving the lower and upper confidence limits.

Author(s)

N. Frerebeau

See Also

Other summary statistics: confidence_binomial(), confidence_mean(), interval_credible(), interval_hdr()

Examples

## Confidence interval for a mean
x <- seq(from = -4, to = 4, by = 0.01)
y <- dnorm(x)

confidence_mean(y, type = "student")
confidence_mean(y, type = "normal")

## Confidence interval for a propotion
confidence_binomial(118, n = 236)

x <- c(35, 74, 22, 69)
confidence_multinomial(x)