dispIndex: Dispersion index

In martindurocher/floodRFA: A R-package for regional frequency of floods

Description

Returns the dispersion index (or variance to mean ratio) to verify the hypothesis of a Homogenous Poisson process.

Usage

dispIndex(obj, k = NULL, ci = FALSE, alpha = 0.05,
  method = "asymptotic", nboot = 10000)

dispIndexPlot(x, ...)

## S3 method for class 'data.frame'
dispIndexPlot(obj, ...)

## S3 method for class 'matrix'
dispIndexPlot(obj, ...)

## S3 method for class 'formula'
dispIndexPlot(form, x, ...)

## S3 method for class 'numeric'
dispIndexPlot(x, dt = NULL, u = 0, method.estim = "mle",
  declust = NULL, r = 1, rlow = 0.75, k = NULL, alpha = 0.05,
  method.ci = "asymptotic", nboot = 1000, xlab = "Threshold (u)",
  ylab = "Dispersion Index", col = "black", lty = 1, lwd = 1,
  col.ci = "black", lty.ci = 3, lwd.ci = 1, ylim = NULL,
  display = TRUE, ...)

Arguments

obj	An output of fitPot.
k	Number of classes. Default value chosen to ensure at least 5 classes and aims at approximately an average 5 events per classe.
ci	Should confident interval and p-value be returns.
alpha	Significance level.
method	Method for computing the confident interval and the p-value. Either 'asymptotic' for chi-squared approximation or 'boot' for bootstrap.
nboot	Number of bootstrap samples.

Details

The function dispIndexPlot will loop across calls of function fitPot and dispIndex and will produce a graphics of the Dispersion index in respect of the threshold u. See respective functions for a description of the function parameters. The points in the plot are returns as a data.frame and parameter display can be set to FALSE to prevent the display of the graphic.

Reference

Lang M, Ouarda TBMJ, Bobée B. (1999) Towards operational guidelines for over-threshold modeling. Journal of Hydrology. Dec 6;225(3):103–17.

See Also

mrlPlot

Examples

fit <- fitPot(flow~date,canadaFlood$daily, u = 1000,
              declust = 'flood', r = 14)

dispIndex(fit, ci = TRUE)

dispIndexPlot(flow~date,canadaFlood$daily,
              u = seq(500,2000, len = 50),
              declust = 'flood', r = 14)

martindurocher/floodRFA documentation built on June 5, 2019, 8:44 p.m.