ci.mu.oneside: One sided confidence interval for mu.

Description

In some situations we may wish to quantify confidence in the region above or below a mean estimate. For instance, a biologist working with an endangered species may be interested in saying: "I am 95 percent confident that the true mean number of offspring is above a particular threshold." In a one-sided situation, we essentially let our confidence be 1- 2\(\alpha\) (instead of 1 - \(\alpha\)). Thus, if our significance level for a two-tailed test is \(\alpha\), our one-tailed significance level will be 2\(\alpha\).

Usage

ci.mu.oneside(data, conf = 0.95, n = NULL, Var = NULL, xbar = NULL, 
summarized = FALSE, N = NULL, fpc = FALSE, tail = "upper")

Arguments

data

A vector of quantitative data. Required if summarized=TRUE.

conf

Level of confidence; 1 - P(type I error).

Sample size. Required if summarized=TRUE.

Var

Sample variance. Required if summarized=TRUE.

xbar

Sample mean. Required if summarized=TRUE.

summarized

Logical. Indicates whether summary statistics instead of raw data should be used.

Population size. Required if summarized=TRUE.

fpc

Logical. Indicating whether finite population corrections should be made.

tail

Indicates what side the one sided confidence limit should be calculated for. Choices are "upper" or "lower".

Value

Returns a list of class = "ci". Default output is a matrix with the sample mean and either the upper or lower confidence limit.

References

Bain, L. J., and Engelhardt, M. (1992) Introduction to Probability and Mathematical Statistics. Duxbury press, Belmont, CA, USA.

Examples

Run this code

# NOT RUN {
ci.mu.oneside(rnorm(100))
# }