MixtureInf (version 1.0-1)

rnormmix: Random sample from a mixture of normals

Description

Generate a random sample for a mixture of univariate normal distributions.

Usage

rnormmix(n, alpha, mean, sd = rep(1, length(alpha)))

Arguments

n

number of samples

alpha

vector of mixture probabilities, with length equal to $m$, the desired number of components.

mean

vector of means of each component.

sd

vector of standard deviations of each component.

Value

• Returns a vector of length $n$ of samples from an $m$-component mixture of univariate normal distributions.

See Also

Functions for mixtures of other standard distributions, such as rbinommix for the binomial and rexpmix for the exponential distribution.

Examples

# Draw random samples from a mixture of two equally likely normal
# distributions, one with mean = -2, s.d. = 1, and the other with
# mean=2, s.d. = 4
x <- rnormmix(200, c(0.5, 0.5), c(-2, 2), c(1, 4))
hist(x, probability=TRUE)
lines(density(x), col='red')