eva (version 0.2.6)

gevrDiag: Diagnostic plots for a fit to the GEVr distribution.

Description

Diagnostic plots for a fit to the GEVr distribution.

Usage

gevrDiag(z, conf = 0.95, method = c("delta", "profile"))

Arguments

z

A class object returned from `gevrFit'.

conf

Confidence level used in the return level plot.

method

The method to compute the return level confidence interval - either delta method (default) or profile likelihood. Choosing profile likelihood may be quite slow.

Value

For stationary models, provides return level plot and density, probability, and quantile plots for each marginal order statistic. The overlaid density is the `true' marginal density for the estimated parameters. For nonstationary models, provides residual probability and quantile plots. In addition, nonstationary models provide plots of the residuals vs. the parameter covariates.

Details

In certain cases the quantile plot may fail, because it requires solving a root equation. See the references for details.

References

Tawn, J. A. (1988). An extreme-value theory model for dependent observations. Journal of Hydrology, 101(1), 227-250.

Smith, R. L. (1986). Extreme value theory based on the r largest annual events. Journal of Hydrology, 86(1), 27-43.

Examples

# NOT RUN {
x <- rgevr(500, 2, loc = 0.5, scale = 1, shape = 0.1)
z <- gevrFit(x)
plot(z)
# }