evd (version 1.2-3)

profile.evd: Method for Profiling evd Objects

Description

Investigates behavior of objective function near the solution represented by fitted.

Usage

## S3 method for class 'evd':
profile(fitted, which = names(fitted$estimate), conf = 0.999,
    mesh = fitted$std.err[which]/2, xmin = rep(-Inf, length(which)),
    xmax = rep(Inf, length(which)), convergence = FALSE, method = "BFGS",
    control = list(maxit = 500), ...)

Arguments

fitted

The original fitted model object.

which

The original model parameters that are to be profiled. By default, all parameters are profiled.

conf

Controls the range over which the parameters are profiled. The confidence coefficient for the confidence interval defined by this range (assuming the usual asymptotic properties) will be at least as large as conf, unless theoretic

mesh

A numeric vector containing one value for each parameter in which. The values represent the distance between the points profiled. By default half the standard errors are used. If the fitted object does not contain standard err

xmin, xmax

Numeric vectors containing one value for each parameter in which. Each value represents the theoretical lower/upper bound of the corresponding parameter. The arguments are typically needed only when a parameter has a theoretic

convergence

Logical; print convergence code after each optimization?

method

The optimization method.

control

Passed to optim. See optim for details.

...

Ignored.

Value

• An object of class "profile.evd"; a list with an element for each parameter being profiled. The elements are matrices. The first column contains the values of the profiled parameter. The second column contains profile deviances. The remaining columns contain the constrained maximum likelihood estimates for the remaining model parameters.

See Also

profile, profile2d, profile2d.evd

Examples

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