Learn R Programming

pscl (version 1.5.9)

hurdle.control: Control Parameters for Hurdle Count Data Regression

Description

Various parameters that control fitting of hurdle regression models using hurdle.

Usage

hurdle.control(method = "BFGS", maxit = 10000, trace = FALSE,
  separate = TRUE, start = NULL, ...)

Value

A list with the arguments specified.

Arguments

method

characters string specifying the method argument passed to optim.

maxit

integer specifying the maxit argument (maximal number of iterations) passed to optim.

trace

logical or integer controlling whether tracing information on the progress of the optimization should be produced (passed to optim).

separate

logical. Should the estimation of the parameters in the truncated count component and hurdle zero component be carried out separately? See details.

start

an optional list with elements "count" and "zero" (and potentially "theta") containing the coefficients for the corresponding component.

...

arguments passed to optim.

Author

Achim Zeileis <Achim.Zeileis@R-project.org>

Details

All parameters in hurdle are estimated by maximum likelihood using optim with control options set in hurdle.control. Most arguments are passed on directly to optim, only trace is also used within hurdle and separate/start control how optim is called.

Starting values can be supplied via start or estimated by glm.fit (default). If separate = TRUE (default) the likelihoods of the truncated count component and the hurdle zero component will be maximized separately, otherwise the joint likelihood is set up and maximized. Standard errors are derived numerically using the Hessian matrix returned by optim. To supply starting values, start should be a list with elements "count" and "zero" and potentially "theta" (a named vector, for models with negative binomial components only) containing the starting values for the coefficients of the corresponding component of the model.

See Also

hurdle

Examples

Run this code
data("bioChemists", package = "pscl")

## default start values
fm1 <- hurdle(art ~ fem + ment, data = bioChemists,
              dist = "negbin", zero = "negbin")

## user-supplied start values and other options
fm2 <- hurdle(art ~ fem + ment, data = bioChemists,
              dist = "negbin",
              zero = "negbin",
              trace=TRUE,
              separate=FALSE,
              start = list(count = c(0.3, -0.2, 0),
                           zero = c(4, -2, 0.8),
                           theta = c(count = 2, zero = 0.1)))

Run the code above in your browser using DataLab