You need to download the source for R. C source is not included with binary
distributions.
Andy
> From: Nathaniel B. Derby
>
> Hello,
>
> Thanks for the help. Unfortunately, my version of R (1.9.1)
> doesn't have that directory (i.e., within $RSRC\src\library,
> there is just a subdirectory entitled "windlgs"), and has
> neither ts.h nor pacf.c in any of its directories. Could it
> be that this function is embedded inside a .dll file (like stats.dll)?
>
>
> thanks,
>
> Nate
>
>
> > It means that in one of the .c source files in
> $RSRC/src/library/stats/src
> > there will be a C function declared as
> >
> > SEXP arma0fa(SEXP, SEXP);
> >
> > (In fact it is declared in ts.h and defined in pacf.c in
> that directory)
>
>
> > Nathaniel B. Derby wrote:
> >> Hi,
> >>
> >> In my ongoing quest to track down the source of an error
> (see message "[R]
> >> optim error in arima" above), I find in the cource code
> for arima0 the
> >> following:
> >>
> >> arma0f <- function(p) {
> >> par <- as.double(fixed)
> >> par[mask] <- p
> >> .Call("arma0fa", G, par, PACKAGE =
"stats")
> >> }
> >>
> >> I would like to know what the function "arma0f" does.
> Does the above mean
> >> that there is a function called "arma0fa" somewhere in
R?
> Where is it? I
> >> couldn't find anything in Rinternals.h.
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html
>
>