Hi,
I am having problems when trying to apply factor analysis in a covariance
matrix,
> factanal(covmat=strip1cmcd, factors=5, control=list(lower=0.0264))
Error in optim(start, FAfn, FAgr, method = "L-BFGS-B", lower = lower,
:
non-finite value supplied by optim
In addition: Warning message:
NaNs produced in: sqrt(diag(cv))
I have searched for possible solutions in messages posted previously. I think
that:
Zeroing the workspace is not a requirement of the original L-BFGS-B code
that I can see. Given that it was originally in Fortran, and Fortran
often does zero it seems a likely symptom, but it does mean that a
variable is being used uninitialized somewhere in the code (converted to
C). It would be better to leave vect alone and to zero the workspace with
a memset call in lbfgsb. (Incidentally, I don't know why S_alloc does not
use memset -- we do require standard C and use in seeral other places.)
--
Brian D. Ripley,
could be relevant to my case. The question is: How can I zero the workspace with
a memset call in lbfgsb?
I have read the Rhelp for windows and tried to zero the workspace from
"RGui.exe" "mim.mem.size" but is not working. Any
suggestions will be very welcome indeed.
Regards
Dr. Gabriela Munoz-Melendez
Environmental Processes and Systems Research Group
Department of Earth Science and Engineering
Imperial College London
SW7 2AZ
Tel: +44 (0)207 594 7369
Fax: +44 (0)207 594 7354
E-mail: g.munoz@imperial.ac.uk
[[alternative HTML version deleted]]
