persp-methods: Methods for Function `persp' in Package `copula'

Description

Methods for function persp to draw perspective plots (of two dimensional distributions from package copula).

Usage

# S4 method for Copula
persp(x, FUN, n.grid = 26, delta = 0,
      xlab = "u1", ylab = "u2",
      zlab = deparse(substitute(FUN))[1], zlim = NULL,
      theta = -30, phi = 30, expand = 0.618,
      ticktype = "detail", …)
# S4 method for mvdc
persp(x, FUN, xlim, ylim, n.grid = 26,
      xlab = "x1", ylab = "x2", zlab = deparse(substitute(FUN))[1],
      theta = -30, phi = 30, expand = 0.618,
      ticktype = "detail", …)

Arguments

a "'>Copula" or a "'>mvdc" object.

FUN

the function to be plotted; typically dCopula or pCopula.

n.grid

the number of grid points used in each dimension. This can be a vector of length two, giving the number of grid points used in x- and y-direction, respectively; the function FUN will be evaluated on the corresponding (x,y)-grid.

delta

A small number in \([0, \frac 1 2)\) influencing the evaluation boundaries. The x- and y- vectors will have the range [0+delta, 1-delta], the default being [0,1].

xlim, ylim

The range of the x and y variables, respectively.

xlab, ylab, zlab, zlim, theta, phi, expand, ticktype, …

Arguments for (the default method of) persp(), the ones enumerated here all with different defaults than there.

Value

invisible; a list with the following components:

x, y

The numeric vectors, as passed to persp.default.

The matrix of evaluated FUN values on the grid as passed to persp.default.

persp

the \(4 \times 4\) transformation matrix returned by persp.default.

Methods

Perspective plots for both "'>copula" or "'>mvdc" objects, see x in the Arguments section.

Examples

Run this code

# NOT RUN {
persp(claytonCopula(2),   pCopula, main = "CDF of claytonCopula(2)")
persp(  frankCopula(1.5), dCopula, main = "Density of frankCopula(1.5)")
persp(  frankCopula(1.5), dCopula, main = "c_[frank(1.5)](.)", zlim = c(0,2))

## Examples with negative tau:
(th1 <- iTau(amhCopula(), -0.1))
persp(amhCopula(th1), dCopula)
persp(amhCopula(th1), pCopula, ticktype = "simple") # no axis ticks
persp(  frankCopula(iTau(  frankCopula(), -0.1)), dCopula)
persp(claytonCopula(iTau(claytonCopula(), -0.1)), dCopula)
##
cCop.2 <- function(u, copula, ...) cCopula(u, copula, ...)[,2]
persp(    amhCopula(iTau(    amhCopula(), -0.1)), cCop.2, main="cCop(AMH...)[,2]")
persp(  frankCopula(iTau(  frankCopula(), -0.1)), cCop.2, main="cCop(frankC)[,2]")
## and  Clayton  also looks "the same" ...

## MVDC Examples ------------------------------------
mvNN <- mvdc(gumbelCopula(3), c("norm", "norm"),
          list(list(mean = 0, sd = 1), list(mean = 1)))
persp(mvNN, dMvdc, xlim=c(-2, 2), ylim=c(-1, 3), main = "Density")
persp(mvNN, pMvdc, xlim=c(-2, 2), ylim=c(-1, 3), main = "Cumulative Distr.")
# }