[R] prcomp problem

[Matthew Wiener]

Hi, everyone.

I'm trying to use prcomp on a fairly large data set.  It has 918 rows, and
the number of columns can be chosen (it's a density function over 200,
300, etc. time steps).

I'm getting the error "error 801 in dsvdc", where 801 is the number of
columns.  By choosing the right number of columns, I can get 
"error 300 in dsvdc" and so on.  There don't seem to be any NaN's or NA's
in the data.  Also, I can run prcomp successfully on random data of the
same size.

princomp successfully finishes, but tells me that there were NaN's
produced by sqrt.  Perhaps this is the numerical instability mentioned in
the documentation (nearly zero but negative numbers).

Does anyone have any ideas why prcomp might have trouble?

Thanks for any help,
			Matt Wiener


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._