plotGPD: Graphical Diagnostic: the Univariate GPD Model

Description Usage Arguments Author(s) Examples

Description

Produces QQ-plot, Probability Plot and a Density Plot of the fitted model versus the empirical one. Another function computes the Return Level Plot of the fitted model.

Usage

1
2
3
## S3 method for class 'uvpot'
plot(x, npy, main, which = 1:4, ask = nb.fig <
length(which) && dev.interactive(),ci = TRUE, ...)

Arguments

x

A fitted object of class 'uvpot'. Generally, an object return by fitgpd

npy

The mean Number of events Per Year - or more generally a block.

main

optional. A string vector corresponding to the title of each plot.

which

a numeric vector which specifies which plot must be drawn : '1' for Probability Plot, '2' for QQ-Plot,'3' for Density Plot and '4' for a Return Level Plot.

ask

Logical. If TRUE, user is asked before each plot.

ci

Logical. If TRUE, the simulated 95% confidence interval is plotted.

...

Other parameters to pass to the plot function.

Author(s)

Mathieu Ribatet

Examples

1
2
3
4
5
6
data(ardieres)
ardieres <- clust(ardieres, 4, 10 / 365, clust.max = TRUE)
fitted <- fitgpd(ardieres[, "obs"], 6, 'mle')
npy <- fitted$nat / 33.4 ##33.4 is the total record length (in year)
par(mfrow=c(2,2))
plot(fitted, npy = npy)

Example output

Warning message:
In clust(ardieres, 4, 10/365, clust.max = TRUE) :
  NA's are not allowed in object ``data''.
Replacing them by -1e6 !!!

POT documentation built on May 2, 2019, 7:30 a.m.