Re: R-beta: spline problems(?)

Ross Ihaka (ihaka@stat.auckland.ac.nz)
Tue, 7 Apr 1998 20:58:47 +1200 (NZST)


Date: Tue, 7 Apr 1998 20:58:47 +1200 (NZST)
From: Ross Ihaka <ihaka@stat.auckland.ac.nz>
Message-Id: <199804070858.UAA16708@stat1.stat.auckland.ac.nz>
To: jlindsey@luc.ac.be, maechler@stat.math.ethz.ch
Subject: Re: R-beta: spline problems(?)

> From: Martin Maechler <maechler@stat.math.ethz.ch>
> Subject: Re: R-beta: spline problems(?)
> Mime-Version: 1.0 (generated by tm-edit 7.95)
?
> >>>>> "Jim" == Jim Lindsey <jlindsey@luc.ac.be> writes:
>
>     Jim> I suspect that this is a problem that I pointed out some time ago
>     Jim> with integers. seq and : produce integers and the C code of spline
>     Jim> is expected doubles. Try as.double() around your 1:nrow(y) and
>     Jim> seq() calls to see if the problem goes away.  Jim

> Jim, this was exactly my own first suspicion, also.
> But it's wrong.

My first reaction also, but it seems that the problem is in the
underlying code.  Which is disapointing as it from the book by
Forsythe, Malcolm and Moler which generally has pretty good code in
it.  Unfortunately, I don't have my book at home, so I can't have a
look at it until tomorrow.

The problem is that there is a divide by zero in the computation of the
coefficients producing Inf, and it is this which causes the message
about NAs (I'll fix the message too :-).

	Ross
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._