The R Project SVN R

\name{numericDeriv}
\alias{numericDeriv}
\title{Evaluate derivatives numerically}
\description{
    \code{numericDeriv} numerically evaluates the gradient of an expression.
}
\usage{
numericDeriv(expr, theta, rho=parent.frame())
}
\arguments{
  \item{expr}{The expression to be differentiated.  The value of this
      expression should be a numeric vector.}
  \item{theta}{A character vector of names of variables used in \code{expr}}
  \item{rho}{An environment containing all the variables needed to
      evaluate \code{expr}}
}
\details{
    This is a front end to the C function \code{numeric_deriv}, which is
    described in \emph{Writing R Extensions}.
}
\value{
    The value of \code{eval(expr, env = rho)} plus a matrix
    attribute called \code{gradient}.  The columns of this matrix are
    the derivatives of the value with respect to the variables listed in
    \code{theta}.
}
\author{Saikat DebRoy \email{saikat@stat.wisc.edu}}
\examples{
myenv <- new.env()
assign("mean", 0., env = myenv)
assign("sd", 1., env = myenv)
assign("x", seq(-3., 3., len = 31), env = myenv)
numericDeriv(quote(pnorm(x, mean, sd)), c("mean", "sd"), myenv)
}
\keyword{models}