eva (version 0.2.6)

gevrProfShape: GEVr Shape Parameter Profile Likelihood Estimation for Stationary Models

Description

Computes the profile likelihood based confidence interval for the shape parameter of the stationary GEVr model.

Usage

gevrProfShape(z, conf = 0.95, plot = TRUE, opt = c("Nelder-Mead"))

Arguments

z

A class object returned from gevrFit.

conf

Confidence level to use. Defaults to 95 percent.

plot

Plot the profile likelihood and estimate (vertical line)?

opt

Optimization method to maximize the profile likelihood, passed to optim. The default method is Nelder-Mead.

Value

Estimate

Estimated shape parameter.

CI

Profile likelihood based confidence interval for the shape parameter.

ConfLevel

The confidence level used.

Examples

# NOT RUN {
# Compare the length of the shape confidence intervals using GEV1 vs. GEV10
set.seed(7)
x <- rgevr(200, 10, loc = 0.5, scale = 1, shape = -0.3)
z1 <- gevrFit(x[, 1])
z2 <- gevrFit(x)
gevrProfShape(z1)
gevrProfShape(z2)
# }