[R] S-Plus RNG (fwd)
mai at ms.uky.edu
Mon Nov 9 15:46:00 CET 1998
>From BMCCULLO at fcc.gov Fri Nov 6 12:50:07 1998
Message-Id: <s642efa3.006 at fcc.gov>
X-Mailer: Novell GroupWise 4.1
Date: Fri, 06 Nov 1998 12:51:24 -0500
From: Bruce McCullough <BMCCULLO at fcc.gov>
To: mai at ms.uky.edu
Subject: S-Plus RNG
Someone forwarded to me your e-mail about RNGs.
I do not know about S-Plus 4.5, but S-Plus 4.0 RNG
was bad. It failed many of Marsaglia's DIEHARD tests.
S-Plus 4.0 documentation indicates that not the
Super-Duper, but a "modified" Super-Duper was used.
Modifying an RNG is not a good idea. It tends to
make the RNG worse. The original Super-Duper
passes all the DIEHARD tests.
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 at stat.math.ethz.ch
More information about the R-help