cdfMclust {mclust}

Cumulative Distribution and Quantiles for a univariate Gaussian mixture distribution

Description

Compute the cumulative density function (cdf) or quantiles from an estimated one-dimensional Gaussian mixture fitted using densityMclust.

Usage

cdfMclust(object, data, ngrid = 100, ...)
quantileMclust(object, p, ...)

Arguments

object

a densityMclust model object.

data

a numeric vector of evaluation points.

ngrid

the number of points in a regular grid to be used as evaluation points if no data are provided.

p

a numeric vector of probabilities.

...

further arguments passed to or from other methods.

Details

The cdf is evaluated at points given by the optional argument data. If not provided, a regular grid of length ngrid for the evaluation points is used.

The quantiles are computed using bisection linear search algorithm.

Value

cdfMclust returns a list of x and y values providing, respectively, the evaluation points and the estimated cdf.

quantileMclust returns a vector of quantiles.

Author(s)

Luca Scrucca

See Also

densityMclust, plot.densityMclust.

Examples

x <- c(rnorm(100), rnorm(100, 3, 2))
dens <- densityMclust(x, plot = FALSE)
summary(dens, parameters = TRUE)
cdf <- cdfMclust(dens)
str(cdf)
q <- quantileMclust(dens, p = c(0.01, 0.1, 0.5, 0.9, 0.99))
cbind(quantile = q, cdf = cdfMclust(dens, q)$y)
plot(cdf, type = "l", xlab = "x", ylab = "CDF")
points(q, cdfMclust(dens, q)$y, pch = 20, col = "red3")

par(mfrow = c(2,2))
dens.waiting <- densityMclust(faithful$waiting)
plot(cdfMclust(dens.waiting), type = "l", 
     xlab = dens.waiting$varname, ylab = "CDF")
dens.eruptions <- densityMclust(faithful$eruptions)
plot(cdfMclust(dens.eruptions), type = "l", 
     xlab = dens.eruptions$varname, ylab = "CDF")
par(mfrow = c(1,1))