Runuran (version 0.7.1)

unuran.cmv-class: Experimental class "unuran.cmv"

Description

The class "unuran.cmv" provides am interface to UNU.RAN objects for continuous multivariate distributions. The interface might be changed in future releases. Do not use unnamed arguments!

Details

Create a new instance of an "unuran.cmv" object using

new ("unuran.cmv", dim=1, pdf=NULL, mode=NULL, center=NULL, ll=NULL, ur=NULL).

[object Object],[object Object],[object Object],[object Object],[object Object]

The user is responsible that the given informations are consistent. It depends on the chosen method which information must be given / are used. It is important, that the mode is contained in the (closure of the) domain.

References

J. Leydold and W. H"ormann (2000-2007): UNU.RAN User Manual, see http://statmath.wu-wien.ac.at/unuran/.

See Also

unuran, unuran.new.

Examples

## Create discrete distribution with given probability density function
mvpdf <- function (x) { exp(-sum(x^2)) }
mvdist <- new("unuran.cmv", dim=2, pdf=mvpdf)
## Make generator (using method HITRO)
mvunr <- unuran.new(mvdist, "hitro")
## Draw sample of size 100
x <- unuran.sample(mvunr, 100)
## make scatter plot of random sample
plot(x)

## now we draw a sample from the same density but restricted to
## the rectangle [0,1]x[0,1]
mvdist <- new("unuran.cmv", dim=2, pdf=mvpdf, mode=c(0,0), ll=c(0,0), ur=c(1,1))
mvunr <- unuran.new(mvdist, "hitro")
x <- unuran.sample(mvunr, 100)
plot(x)

## draw a sample from the same density but restricted to
## the the first quadrant
mvdist <- new("unuran.cmv", dim=2, pdf=mvpdf, mode=c(0,0), ll=c(0,0), ur=c(Inf,Inf))
mvunr <- unuran.new(mvdist, "hitro")
x <- unuran.sample(mvunr, 100)
plot(x)

## draw a sample from the same density but restricted to
## the rectangle [1,2]x[1,2]
## (Don't forget to provide a starting point for the HITRO method by
## setting 'center'
mvdist <- new("unuran.cmv", dim=2, pdf=mvpdf, center=c(1.1,1.1), ll=c(1,1), ur=c(2,2))
mvunr <- unuran.new(mvdist, "hitro")
x <- unuran.sample(mvunr, 100)
plot(x)