[R] Error with grad() for numerical differential of a function

Berend Hasselman bhh at xs4all.nl
Sun Mar 10 16:57:53 CET 2013


On 10-03-2013, at 16:43, Oleguer Plana Ripoll <oleguerplana at gmail.com> wrote:

> Hello everyone,
> 
> I have programmed a function and, among other things, it has to compute the differential of a function. I have been using the function grad() and I have programmed some simulated studies. I have testes with 72,576 different combinations of the initial values and now I got an error in only 4 situations.
> 
> The error comes from the function grad() and I don't understand why. This is the output:
> Error in grad.default(Sstar, x = t, dist1 = T1pdist, dist2 = T2pdist,  : 
>  function returns NA at 3.90625e-071.01927622979798e-087.7105723770202e-075.27096223871154e-087.28540377612885e-071.25230637383194e-076.56019362616806e-072.21329924168263e-075.59920075831737e-073.324709613353e-074.487790386647e-070.0001000016964206937.79553579306956e-072.72822299391765e-087.53967770060824e-078.56180755521809e-086.95631924447819e-071.70797994270076e-076.10452005729924e-072.75627788007242e-075.05622211992758e-07 distance from x.
> 
> Anyone knows when returns a NA this function? Anyone knows other function to make numerical approximations of the differential?
> 
> Thank you for your help,
> Oleguer
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.


Not enough information to give a non flippant reply.
Which package(s) are you using?
What is your function?
Provide a small reproducible example.

Please read the posting guide (link at bottom of each posting to R-help).

Berend



More information about the R-help mailing list