[R] Is there an R-SQUARE function?

Thomas Lumley thomas at biostat.washington.edu
Wed Sep 29 18:10:58 CEST 1999

On Wed, 29 Sep 1999, Stuart Luppescu wrote:

> On 29-Sep-99 Thomas Lumley wrote:
> > The "leaps" package on CRAN does this.  This is normally called
> > all-subsets regression rather than R-SQUARE (or, to be fair, "leaps")
> This interests me a lot. But when I tried to use the package, I got this
> message:
> > library(leaps)
> Error in dyn.load(file) : unable to load shared library
> "/usr/lib/R/library/leaps/libs/leaps.so":
>   /usr/lib/R/library/leaps/libs/leaps.so: undefined symbol: do_lio
> Did I make some mistake in installing the package, or what?
> I'm running R 0.65 on RedHat Linux 6.0 (intel) with kernel 2.2.12; leaps is 
> Aug 17 12:45 leaps_2.0.tar.gz

It sounds like there is a problem with your Fortran compiling or linking.
On my Debian system using g77, nm leaps.so shows that the symbol do_lio is
defined, and on Solaris using Sun's f77 it isn't even exported.

What compilers are you using, and did you get any error messages when
installing the package?


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 mailing list