optimx (version 2018-7.10)

grnd: A reorganization of the call to numDeriv grad() function.

Description

Provides a wrapper for the numDeriv approximation to the gradient of a user supplied objective function userfn.

Usage

grnd(par, userfn, ...)

Arguments

par

A vector of parameters to the user-supplied function fn

userfn

A user-supplied function

...

Other data needed to evaluate the user function.

Value

grnd returns an approximation to the gradient of the function userfn

Details

The Richardson method is used in this routine.

Examples

# NOT RUN {
cat("Example of use of grnd\n")
require(numDeriv)
myfn<-function(xx, shift=100){
    ii<-1:length(xx)
    result<-shift+sum(xx^ii)
}
xx<-c(1,2,3,4)
ii<-1:length(xx)
print(xx)
gn<-grnd(xx,myfn, shift=0)
print(gn)
ga<-ii*xx^(ii-1)
cat("compare to\n")
print(ga)
# }