fit.hyperb {HyperbolicDist} | R Documentation |
Fits a hyperbolic distribution to data. Displays the histogram, log-histogram (both with fitted densities) and qqplot for the fit which has the maximum likelihood.
fit.hyperb(x, freq = NULL, breaks = NULL, theta.start = NULL, start.values = c("all"), method = c("BFGS"), max.lh = FALSE, plots = TRUE, leave.on = FALSE, controlbfgs = list(maxit = 100), controlnm = list(maxit = 1000), maxitnlm = 1500, ...)
x |
data vector |
freq |
a vector of weights with length equal to length(x) |
breaks |
breaks for histogram, defaults to those generated by
hist(x,right=F,plot=F) |
theta.start |
a user specified starting parameter vector taking
the form c(pi,zeta,delta,mu) |
start.values |
vector of the different starting values to consider. See Details |
method |
vector of the different optimisation methods to consider. See Details |
max.lh |
logical; if TRUE , function only outputs for the
start.values /method combination that results in the highest
likelihood |
plots |
logical; if FALSE suppresses printing of the histogram,
log-histogram and qqplot |
leave.on |
for use with plotting devices. When TRUE does not
close off the plotting device (eg. postscript ) after writing the
3 plots |
controlbfgs |
a list of control parameters for optim when using
the "BFGS" optimisation |
controlnm |
a list of control parameters for optim
when using the "Nelder-Mead" optimisation |
maxitnlm |
a positive integer specifying the maximum number of
iterations when using the "nlm" optimisation |
... |
passes arguments to par , hist , log.hist
and qqplot |
Entries in the start.values vector are from the following:
"bn"
"fn"
"sl"
"us"
The three optimisation methods currently available are:
"BFGS"
"BFGS"
as documented
in optim
"Nelder-Mead"
optim
"nlm"
nlm
function in RA list with components
pars |
a dataframe displaying the results of maximisation.
Consists of columns for pi , zeta , delta , mu ,
LogLikelihood , Convergence and Iterations .
See the relevant documentation (either optim or nlm )
for details on convergence |
breaks |
the breaks used |
starting.values |
a dataframe displaying the various starting values considered |
David Scott d.scott@auckland.ac.nz, Ai-Wei Lee, Jennifer Tso, Richard Trendall
Barndorff-Nielsen, O. (1977) Exponentially decreasing distributions for the logarithm of particle size, Proc. Roy. Soc. Lond., A353, 401–419.
Fieller, N. J., Flenley, E. C. and Olbricht, W. (1992) Statistics of particle size data. Appl. Statist., 41, 127–146.
optim
, nlm
, par
,
hist
, log.hist
, qqplot
and dskewlap
theta <- c(2,2,2,2) data.vector <- rhyperb(500,theta) ## See how well fit.hyperb works fit.hyperb(data.vector) ## Use nlm instead of default fit.hyperb(data.vector,method="nlm")