ghyp-mle.ghyp-classes {ghyp} | R Documentation |
The class “ghyp” basically contains the parameters of a generalized
hyperbolic distribution.
The class “mle.ghyp” inherits from
the class “ghyp”. The class “mle.ghyp” adds some additional slots
which contains information about the fitting
procedure. Namely the
number of iterations n.iter
, the log likelihood value llh
,
the Akaike Information Criterion aic
, a boolean vector fitted.params
stating which parameters were fitted,
a boolean converged
whether the fitting procedure converged or not,
an error.code
which stores the status of a possible error and
the corresponding error.message
. In the univariate case the parameter variance
is also stored in parameter.variance
.
Objects should only be created by calls to the constructors ghyp
,
hyp
, NIG
, VG
and student.t
or by calls to the fitting routines like fit.ghypuv
,
fit.ghypmv
, fit.hypuv
, fit.hypmv
et cetera.
Slots of class ghyp:
call
:"call"
.lambda
:"numeric"
.alpha.bar
:"numeric"
.chi
:"numeric"
.psi
:"numeric"
.mu
:"numeric"
.sigma
:"numeric"
in the univariate case and
"matrix"
in the multivariate case.gamma
:"numeric"
.model
:"character"
.dimension
:"numeric"
.expected.value
:"numeric"
.variance
:"numeric"
in the univariate case and
"matrix"
in the multivariate case.data
:"matrix"
for multivariate distributions and
of class "numeric"
for univariate distributions. When an object of class
ghypmv
is instantiated the user can decide whether
data should be stored within the object or not. This is the default and may be useful
when fitting eneralized hyperbolic distributions to data and
perform further analysis afterwards.parametrization
:"character"
.
These are currently either "lambda.chi.psi"
or
"lambda.alpha.bar"
.Slots added by class mle.ghyp:
n.iter
:"numeric"
.llh
:"numeric"
.converged
:"logical"
.error.code
:"numeric"
.error.message
:"character"
.fitted.params
:"logical"
.aic
:"numeric"
.parameter.variance
:"matrix"
.
Class “mle.ghyp” extends class "ghyp"
, directly.
A “pairs” method (see pairs
).
A “hist” method (see hist
).
A “plot” method (see plot
).
A “lines” method (see lines
).
A “coef” method (see coef
).
A “mean” method (see mean
).
A “vcov” method (see vcov
).
A “transform” method (see transform
).
A “[.ghyp” method (see [
).
A “logLik” method for objects of class “mle.ghyp” (see logLik
).
An “AIC” method for objects of class “mle.ghyp” (see AIC
).
A “summary” method for objects of class “mle.ghyp” (see summary
).
When showing special cases of the generalized hyperbolic distribution the corresponding fixed parameters are not printed.
David Lüthi
optim
for an interpretation of error.code
and error.message
.
ghyp
, hyp
, NIG
, VG
, student.t
for constructors
of the class ghyp
.
fit.ghypuv
, fit.ghypmv
et cetera for the fitting routies and constructors of the class
mle.ghyp
.
data(smi.stocks) multivariate.fit <- fit.ghypmv(data = smi.stocks, opt.pars = c(lambda = FALSE, alpha.bar = FALSE), lambda=2) summary(multivariate.fit) vcov(multivariate.fit) mean(multivariate.fit) logLik(multivariate.fit) AIC(multivariate.fit) coef(multivariate.fit) univariate.fit <- multivariate.fit[1] hist(univariate.fit) plot(univariate.fit) lines(multivariate.fit[2])