evd (version 1.2-3)

pcint: Profile Likelihood Confidence Intervals

Description

Calculates profile likelihood confidence intervals from an object of class "profile.evd".

Usage

pcint(prof, which = names(prof), ci = 0.95)

Arguments

prof

An object of class profile.evd.

which

The original model parameters for which profile likelihood confidence intervals are calculated. By default intervals are calculated for all the parameters that have been profiled in prof.

ci

Confidence coefficient (but see Warning).

Value

• A list with one element for each parameter in which. Each element is a numeric vector of length two giving the lower and upper limits of the confidence intervals (but see Warning).

Warning

The calculated intervals may not be confidence intervals with (asymptotic) confidence coefficient ci, because the usual asymptotic properties of maximum likelihood estimators may not hold! The usual asymptotic properties hold when the shape parameter(s) is(are) greater than $-0.5$, and when the parameters are not on the edge of the parameter space (Smith, 1985). Fortunately, this is usually the case.

References

Smith, R. L. (1985) Maximum likelihood estimation in a class of non-regular cases. Biometrika, 72, 67--90.

See Also

profile.evd

Examples

uvdata <- rgev(100, loc = 0.13, scale = 1.1, shape = 0.2)
M1 <- fgev(uvdata)
M1P <- profile(M1)
pcint(M1P)
plot(M1P)