plot-methods {GSM}

Plot of a Gamma Shape Mixture Model

Description

plot method for class "gsm". This function plots the output of a Gamma Shape Mixture estimation procedure.

Usage

## S4 method for signature 'gsm,missing'
plot(x, ndens = 5, xlab = "x", ylab = "density", nbin = 10,
		histogram = FALSE, bands = FALSE, confid = .95, start = 1, ...)

Arguments

x

object of class "gsm"; a list returned by the estim.gsm or estim.gsm_theta functions.

ndens

number of simulated density curves to plot.

xlab

a title for the x axis.

ylab

a title for the y axis.

nbin

number of bins for the histogram.

histogram

logical; if TRUE the histogram is plotted on the figure.

bands

logical; if TRUE the 95% credibility bands are overimposed on the density graph.

confid

confidence level for the pointwise credibility bands around the density estimate.

start

MCMC run to start from.

...

further arguments passed to or from other methods.

Details

To produce a standard histogram with the estimated density curve superimposed on it, simply set ndens to 0 and histogram to TRUE.

Value

List with the following components:

xval

horizontal coordinates.

yval

vertical coordinates (pointwise density posterior means).

Author(s)

Sergio Venturini [e-mail]

References

Venturini, S., Dominici, F. and Parmigiani, G. (2008), "Gamma shape mixtures for heavy-tailed distributions". Annals of Applied Statistics, Volume 2, Number 2, 756–776. http://projecteuclid.org/euclid.aoas/1215118537

See Also

estim.gsm, estim.gsm_theta, summary-methods, predict-methods.

Examples

set.seed(2040)
y <- rgsm(500, c(.1, .3, .4, .2), 1)
burnin <- 5
mcmcsim <- 10
J <- 250
gsm.out <- estim.gsm(y, J, 300, burnin + mcmcsim, 6500, 340, 1/J)
par(mfrow = c(3, 2))
plot(gsm.out)
plot(gsm.out, ndens = 0, nbin = 20, start = (burnin + 1))
plot(gsm.out, ndens = 0, nbin = 20, histogram = TRUE, start = (burnin + 1))
plot(gsm.out, ndens = 0, nbin = 20, histogram = TRUE, bands = TRUE, start = (burnin + 1))
plot(gsm.out, ndens = 5, nbin = 20, histogram = TRUE, bands = TRUE, start = (burnin + 1))
plot(gsm.out, ndens = 0, nbin = 20, bands = TRUE, start = (burnin + 1))