The R Project SVN R

% $Id: profiler.nls.Rd,v 1.7 2001/08/25 22:17:32 hornik Exp $
\name{profiler.nls}
\alias{profiler.nls}
\title{ Constructor for Profiler Objects from nls Objects}
\description{
  Create a profiler object for the model object \code{fitted} of class
  \code{\link{nls}}.
}
\usage{
\method{profiler}{nls}(fitted, \dots)
}
\arguments{
  \item{fitted}{the original fitted model object of class
    \code{\link{nls}}.}
  \item{\dots}{  Additional parameters. None are used.}
}
\value{
  An object of class \code{profiler.nls} which is a list with function
  elements
  \item{getFittedModel()}{
    the \code{\link{nlsModel}} object corresponding to \code{fitted}
  }
  \item{getFittedPars()}{
    See documentation for \code{\link{profiler}}
  }
  \item{setDefault(varying, params)}{
    See documentation for \code{\link{profiler}}
  }
  \item{getProfile(varying, params)}{
    In the returned list, \code{fstat} is the ratio of change in
    sum-of-squares and the residual standard error.
    
    For other details, see documentation for \code{\link{profiler}}
  }
}
\section{WARNING}{
  When using setDefault and getProfile together, the internal state of
  the fitted model may get changed. So after completing the profiling
  for a parameter, the internal states should be restored by a call to
  setDefault without any arguments. For example see below or the source
  for \code{\link{profile.nls}}.
}
\references{
  Bates, D.M. and Watts, D.G. (1988),
  \emph{Nonlinear Regression Analysis and Its Applications},
  Wiley
}
\author{Douglas M. Bates and Saikat DebRoy}
\seealso{
  \code{\link{nls}},
  \code{\link{nlsModel}},
  \code{\link{profiler}},
  \code{\link{profile.nls}}
}
\examples{
data( BOD )
## obtain the fitted object
fm1 <- nls(demand ~ SSasympOrig( Time, A, lrc ), data = BOD)
## get the profile for the fitted model
prof1 <- profiler( fm1 )
## profile with A fixed at 16.0
prof1$getProfile(c(FALSE, TRUE), 16.0)
## vary lrc
prof1$setDefault(varying = c(FALSE, TRUE))
## fix A at 14.0 and starting estimate of lrc at -0.2
prof1$setDefault(params = c(14.0, -0.2))
## and get the profile
prof1$getProfile()
## finally, set defaults back to original estimates
prof1$setDefault()
}
\keyword{nonlinear}
\keyword{regression}
\keyword{models}