Skip to content

Ltsreg and nsamp="exact"

2 messages · Christopher Adolph, Brian Ripley

#
I'm trying to use least trimmed squares using ltsreg with nsamp="exact".
When I use the following:

rg <- ltsreg(x,y,nsamp="exact")

I get:

Error in lqs.default(x, y, nsamp = "exact", method = "lts") :
        NAs in foreign function call (arg 10)
In addition: Warning message:
NAs introduced by coercion

Incidentally, there are no missings in x or y, and when I run

rg <- ltsreg(x,y)

everything is fine.

Any ideas?

Thanks

Chris Adolph
#
Are subsets of your data collinear?
On Wed, 18 Jun 2003, Christopher Adolph wrote: