[S] Error in AIMD/Norm

Marc Feldesman (feldesmanm@pdx.edu)
Sat, 21 Nov 1998 08:20:49 -0800


Sorry to post this message here, but Joe Shafer is currently unreachable.
I'm trying to use his library for multiple imputation. There are two
S-Plus variants of the library -- AIMD, ported by Brian Ripley, and NORM
available on Shafer's web site. I've tried both variants with one of my
data set - a relatively straightforward file with 227 cases and 16
variables (all numeric).

I've not managed to get even the preliminaries run because both versions
(i.e. those in AIMD and in NORM) fail during the essential starting
function "prelim.norm" with the following error:

joe<-prelim.norm(as.matrix(apehum))
Error in .Fortran("ctrsc",: "CTRSC" is not a symbol i
n the load table
Dumped
Warning messages:
1067 missing values generated coercing from charact
er to single in: storage.mode(x) <- "single"

Since there are no characters in the file (and I've verified this) the
message is utterly meaningless to me. Can someone give me a clue what
might be going on here. I've even entered sample data directly from
Shafer's book and get the .Fortran error.

I'm using SPlus 4.5, SP#2 under Windows 95.

Thanks for your help.

Dr. Marc R. Feldesman
Professor and Chairman
Anthropology Department
Portland State University
P.O. Box 751
Portland, Oregon 97207
email: feldesmanm@pdx.edu
phone: 503-725-3081
fax: 503-725-3905
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news