ripley@stats.ox.ac.uk
2001-Mar-21 17:21 UTC
[Rd] Incorrect values in non-central chisq values on Linux (PR#881)
On the system below
dchisq(7.2, df=2,ncp=20)
[1] 0.00804528
Solaris 2.7 gives
[1] 0.01175302
which is correct, as can be seen from
x<-seq(0,50,.1)
y<-x
for(i in 1:length(x)){
y[i]<-dchisq(x[i],df=2,ncp=20)}
plot(x,y,typ="l")
The problem is that q in dnchisq.c can be 1, and then errorbound
should be Inf. It is on Solaris, but -105822722841527.296875 on Linux
(so it has been evaluated q to greater than one).
I am about to commit a patch for 1.2.3.
--please do not edit the information below--
Version:
platform = i686-pc-linux-gnu
arch = i686
os = linux-gnu
system = i686, linux-gnu
status major = 1
minor = 2.2
year = 2001
month = 02
day = 26
language = R
Search Path:
.GlobalEnv, package:ctest, Autoloads, package:base
--
Brian D. Ripley, ripley@stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272860 (secr)
Oxford OX1 3TG, UK Fax: +44 1865 272595
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel 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-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._