Revision e45edf477b8874a1a9fa0db5c018e97af0632201 authored by Yohan Chalabi on 14 September 2012, 00:00:00 UTC, committed by Gabor Csardi on 14 September 2012, 00:00:00 UTC
1 parent 60e3e5c
dist-ghtFit.Rd
\name{ghtFit}
\alias{ghtFit}
\alias{ghtFit}
\title{GHT Distribution Fit}
\description{
Estimates the distributional parameters for a
generalized hyperbolic Student-t distribution.
}
\usage{
ghtFit(x, beta = 0.1, delta = 1, mu = 0, nu = 10,
scale = TRUE, doplot = TRUE, span = "auto", trace = TRUE,
title = NULL, description = NULL, \dots)
}
\arguments{
\item{beta, delta, mu}{
numeric values.
\code{beta} is the skewness parameter in the range \code{(0, alpha)};
\code{delta} is the scale parameter, must be zero or positive;
\code{mu} is the location parameter, by default 0.
These are the parameters in the first parameterization.
}
\item{nu}{
defines the number of degrees of freedom.
Note, \code{alpha} takes the limit of \code{abs(beta)},
and \code{lambda=-nu/2}.
}
\item{x}{
a numeric vector.
}
\item{scale}{
a logical flag, by default \code{TRUE}. Should the time series
be scaled by its standard deviation to achieve a more stable
optimization?
}
\item{doplot}{
a logical flag. Should a plot be displayed?
}
\item{span}{
x-coordinates for the plot, by default 100 values
automatically selected and ranging between the 0.001,
and 0.999 quantiles. Alternatively, you can specify
the range by an expression like \code{span=seq(min, max,
times = n)}, where, \code{min} and \code{max} are the
left and right endpoints of the range, and \code{n} gives
the number of the intermediate points.
}
\item{trace}{
a logical flag. Should the parameter estimation process be
traced?
}
\item{title}{
a character string which allows for a project title.
}
\item{description}{
a character string which allows for a brief description.
}
\item{\dots}{
parameters to be parsed.
}
}
\value{
returns a list with the following components:
\item{estimate}{
the point at which the maximum value of the log liklihood
function is obtained.
}
\item{minimum}{
the value of the estimated maximum, i.e. the value of the
log liklihood function.
}
\item{code}{
an integer indicating why the optimization process terminated.\cr
1: relative gradient is close to zero, current iterate is probably
solution; \cr
2: successive iterates within tolerance, current iterate is probably
solution; \cr
3: last global step failed to locate a point lower than \code{estimate}.
Either \code{estimate} is an approximate local minimum of the
function or \code{steptol} is too small; \cr
4: iteration limit exceeded; \cr
5: maximum step size \code{stepmax} exceeded five consecutive times.
Either the function is unbounded below, becomes asymptotic to a
finite value from above in some direction or \code{stepmax}
is too small.
}
\item{gradient}{
the gradient at the estimated maximum.
}
\item{steps}{
number of function calls.
}
}
\details{
The function \code{\link{nlm}} is used to minimize the "negative"
maximum log-likelihood function. \code{nlm} carries out a minimization
using a Newton-type algorithm.
}
\examples{
## ghtFit -
# Simulate Random Variates:
set.seed(1953)
## ghtFit -
# Fit Parameters:
}
\keyword{distribution}
Computing file changes ...