PlotMrl: Diagnostic tools for peaks over threshold analysis

In martindurocher/floodStat: FloodNet Regional Frequency Analysis

Description

Produce mean residual Life, quantite-quantile, probability-probability, histogram of the excesses, Stability plot for the parameter of the GPA.

Usage

PlotMrl(form, x, u, declust = NULL, r = 1, rlow = 0.75,
  alpha = 0.05, ylab = "Mean Residual Life", xlab = "Threshold",
  col = "black", lty = 1, lwd = 1, col.ci = "black", lty.ci = 3,
  lwd.ci = 1, ylim = NULL, display = TRUE, ...)

Arguments

x, dt, form	Sample and time of observation. A formula can also be passed, in which case x is a data.frame.
u	Series of candidate thresholds.
alpha	Confidence interal with level 1-alpha/2.
...	Others arguments are passed to function plot and which.floodPeaks
method	Estimation method.
param	Choice of the parameter to display. Either 'alpha' or 'kappa'.

Details

The function PlotPotShape will loop across calls of function FitPot and will produce a graphics of the shape parameter in respect of the threshold u. See the respective functions for a description of the function parameters.

See Also

FitPot, which.floodPeaks.

Examples

## Find list of candidate thresholds
lstu <- seq(500,2500, len = 50)

PlotMrl(flow~date,flowStJohn, u = lstu, declust = 'wrc', r = 14)

PlotPotShape(flow~date,flowStJohn, u = lstu, declust = 'wrc', r = 14)
PlotPotShape(flow~date,flowStJohn, u = lstu,
            declust = 'wrc', r = 14, param = 'alpha', method = 'mle2')


fit <- FitPot(flow~date,flowStJohn, u = 997, declust = 'wrc', r = 14)
ppplot(fit)
qqplot(fit, ci = TRUE)
hist(fit)

martindurocher/floodStat documentation built on May 31, 2019, 12:42 a.m.