Generator Microsoft Word 11 (filtered medium) Hi,

I'm the mannova package maintainer. We used La.svd(X, method="dgesvd") in 
maanova package before. After R-2.3.0, the old La.svd() method was deprecated 
for option method="dgesvd". I changed maanova code correspondingly, which will 
call method="dgesdd" instead. But after that, we keep getting below error 
message from La.svd() if the data object is big.

Error in La.svd(X) : error code 1 from Lapack routine 'dgesdd'

Would you please help us to figure out what's the cause of this? We tried the 
small and big microarray data set. Small one does not cause this problem, but 
the bigger dataset causes this error. Is there any limitation of using La.svd() 
or is there any parameter we can specify to enlarge the capacity of La.svd()?

Please see the attached R script and data files. Sorry for the huge data file. 
But that' s the smallest I can make to cause the error message.

Thank you very much for your help!

Lei



_______________________
Lei Wu
Scientific Software Engineer
The Jackson Laboratory
600 Main St.
Bar Harbor, ME 04609
Tel: 207-288-6715



        [[alternative HTML version deleted]]

______________________________________________
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel

Reply via email to