\name{mob_control}

\alias{mob_control}

\title{Control Parameters for Model-based Partitioning}

\description{

  Various parameters that control aspects the fitting algorithm

  for recursively partitioned \code{\link{mob}} models.

}

\usage{

mob_control(alpha = 0.05, bonferroni = TRUE, minsplit = 20, trim = 0.1,

  objfun = deviance, breakties = FALSE, parm = NULL, verbose = FALSE)

}

\arguments{

  \item{alpha}{numeric significance level. A node is splitted when

    the (possibly Bonferroni-corrected) \eqn{p} value for any parameter

    stability test in that node falls below \code{alpha}.}

  \item{bonferroni}{logical. Should \eqn{p} values be Bonferroni corrected?}

  \item{minsplit}{integer. The minimum number of observations (sum of the

    weights) in a node.}

  \item{trim}{numeric. This specifies the trimming in the parameter instability

    test for the numerical variables. If smaller than 1, it is interpreted

    as the fraction relative to the current node size.}

  \item{objfun}{function. A function for extracting the minimized value of

    the objective function from a fitted model in a node.}

  \item{breakties}{logical. Should ties in numeric variables be broken

    randomly for computing the associated parameter instability test?}

  \item{parm}{numeric or character. Number or name of model parameters

    included in the parameter instability tests (by default all parameters

    are included).}

  \item{verbose}{logical. Should information about the fitting process

    of \code{\link{mob}} (such as test statistics, \eqn{p} values, selected

    splitting variables and split points) be printed to the screen?}

}

\details{

  See \code{\link{mob}} for more details and references.

}

\seealso{\code{\link{mob}}}

\value{

  A list of class \code{mob_control} containing the control parameters.

}

\keyword{misc}