binomCI: Binomial Confidence Interval

In JVAdams/jvamisc: A Collection of Utility Functions

Description

Calculates the binomial confidence interval from a sample, using the normal approximation. Uses Louis (1981) if only failures or only successes were observed.

Usage

binomCI(x, y = NULL, na.rm = TRUE, alpha = 0.05, prob = TRUE)

Arguments

x	A vector of 0s and 1s, or (if y is also given) a scalar, the number of successes.
y	A scalar, the number of failures, default NULL.
na.rm	A logical, whether to remove NAs from the data, default TRUE.
alpha	A scalar, the desired confidence level, default 0.05.
prob	A logical, whether to output results as probabilities, default TRUE, or counts.

Value

A named vector with the Mean, lower and upper confidence limits (L and U), and the number of observations N.

References

Thomas A. Louis. 1981. Confidence intervals for a binomial parameter after observing no successes. The American Statistician 35(3):154. http://amstat.tandfonline.com/doi/abs/10.1080/00031305.1981.10479337?journalCode=utas20#.U3t2EvldX64

Examples

binomCI(c(0, 0, 0, 0, 1, 1))
binomCI(2, 4, prob=FALSE)

JVAdams/jvamisc documentation built on Aug. 11, 2021, 6:43 a.m.