hyperbFitStart: Find Starting Values for Fitting a Hyperbolic Distribution

View source: R/hyperbFitStart.R

hyperbFitStartR Documentation

Find Starting Values for Fitting a Hyperbolic Distribution

Description

Finds starting values for input to a maximum likelihood routine for fitting hyperbolic distribution to data.

Usage

  hyperbFitStart(x, breaks = NULL, startValues = "BN",
                 ThetaStart = NULL, startMethodSL = "Nelder-Mead",
                 startMethodMoM = "Nelder-Mead", ...)
  hyperbFitStartMoM(x, startMethodMoM = "Nelder-Mead", ...)

Arguments

x

Data vector.

breaks

Breaks for histogram. If missing, defaults to those generated by hist(x, right = FALSE, plot = FALSE).

startValues

Vector of the different starting values to consider. See Details.

ThetaStart

Starting values for Theta if startValues = "US".

startMethodSL

Method used by call to optim in finding skew Laplace estimates.

startMethodMoM

Method used by call to optim in finding method of moments estimates.

...

Passes arguments to optim.

Details

Possible values of the argument startValues are the following:

  • "US"User-supplied.

  • "BN"Based on Barndorff-Nielsen (1977).

  • "FN"A fitted normal distribution.

  • "SL"Based on a fitted skew-Laplace distribution.

  • "MoM"Method of moments.

If startValues = "US" then a value must be supplied for ThetaStart.

If startValues = "MoM", hyperbFitStartMoM is called. These starting values are based on Barndorff-Nielsen et al (1985).

If startValues = "SL", or startValues = "MoM" an initial optimisation is needed to find the starting values. These optimisations call optim.

Value

hyperbFitStart returns a list with components:

ThetaStart

A vector with elements pi, lZeta (log of zeta), lDelta (log of delta), and mu giving the starting value of Theta.

xName

A character string with the actual x argument name.

breaks

The cell boundaries found by a call to hist.

midpoints

The cell midpoints found by a call to hist.

empDens

The estimated density found by a call to hist.

hyperbFitStartMoM returns only the method of moments estimates as a vector with elements pi, lZeta (log of zeta), lDelta (log of delta), and mu.

Author(s)

David Scott d.scott@auckland.ac.nz, Ai-Wei Lee, Jennifer Tso, Richard Trendall, Thomas Tran

References

Barndorff-Nielsen, O. (1977) Exponentially decreasing distributions for the logarithm of particle size, Proc. Roy. Soc. Lond., A353, 401–419.

Barndorff-Nielsen, O., Bl<e6>sild, P., Jensen, J., and S<f6>renson, M. (1985). The fascination of sand. In A celebration of statistics, The ISI Centenary Volume, eds., Atkinson, A. C. and Fienberg, S. E., pp. 57–87. New York: Springer-Verlag.

Fieller, N. J., Flenley, E. C. and Olbricht, W. (1992) Statistics of particle size data. Appl. Statist., 41, 127–146.

See Also

HyperbolicDistribution, dskewlap, hyperbFit, hist, and optim.

Examples

Theta <- c(2,2,2,2)
dataVector <- rhyperb(500,Theta)
hyperbFitStart(dataVector,startValues="FN")
hyperbFitStartMoM(dataVector)
hyperbFitStart(dataVector,startValues="MoM")

HyperbolicDist documentation built on March 18, 2022, 6:23 p.m.