gpdRangeFit function

Estimate generalized Pareto distribution parameters over a range of values

Estimate generalized Pareto distribution parameters over a range of values, using maximum (penalized) likelihood.

gpdRangeFit(data, umin=quantile(data, .05), umax=quantile(data, .95),
nint = 10, penalty = "gaussian", priorParameters = NULL, alpha=0.05,
cov="observed")
## S3 method for class 'gpdRangeFit'
print(x, ...)
## S3 method for class 'gpdRangeFit'
summary(object, ...)
## S3 method for class 'summary.gpdRangeFit'
print(x, ...)
## S3 method for class 'gpdRangeFit'
plot(x, xlab = "Threshold", ylab = NULL, main = NULL, addNexcesses=TRUE, ...)
## S3 method for class 'gpdRangeFit'
ggplot(data, mapping, xlab="Threshold", ylab=NULL,
main=NULL, fill="orange", col="blue", addNexcesses = TRUE, textsize=4, ...,
environment)

Arguments

• data: The data vector to be modelled.
• umin: The minimum threshold above which to estimate the parameters.
• umax: The maximum threshold above which to estimate the parameters.
• nint: The number of thresholds at which to perform the estimation.
• penalty: The type of penalty to be used in the maximum penalized likelihood estimation. Should be either "gaussian" or "none". Defaults to "gaussian".
• priorParameters: Parameters to be used for the penalty function. See the help for evm for more informaiton.
• alpha: 100(1 - alpha)% confidence intervals will be plotted with the point estimates. Defaults to alpha = 0.05.
• cov: How to compute the covariance matrix of the parameters. Defaults to cov = "observed" in which case the observed information matrix is used, if the info element of the texmexFamily object is present. See more detailed documentation of this argument in evm.
• x, object: Arguments to print and summary functions.
• xlab: Label for the x-axis.
• ylab: Label for the y-axis.
• main: The main title.
• addNexcesses: Annotate top axis with numbers of threshold excesses arising with the corresponding values of threshold on the bottom axis.
• col: Colour of the line on the threshold stability plot.
• fill: Colour of the pointwise confidence region on the threshold stability plots.
• textsize: Size of text on the plot (ggplot). Defaults to textsize=4.
• ...: Arguments to plot.
• mapping, environment: Not used.

Details

This is Stuart Coles' gpd.fitrange, as it appears in the ismev

package, refactored into a function that does the computations, and method functions. The function uses evm internally and uses the default options for that function.

Note this function does not extend to assessing model fit when there are covariates included in the model.

Examples

par(mfrow=c(1,2))
plot(gpdRangeFit(rain))

See Also

evm

Author(s)

Stuart Coles, Janet E Heffernan, Harry Southworth