Thanks, Roger. And thanks for alerting me to the possible issues with the
coefficient covariance matrix. For my immediate purposes, this yields
plausible results.
On Sun, Jul 3, 2011 at 10:54 AM, Roger Bivand wrote:
> On Sat, 2 Jul 2011, Jason Sorens wrote:
>
> I'm interested in
I'm interested in testing linear combinations of coefficients after models
like spautolm, errorsarlm, and lagsarlm in the spdep package. I'm used to
using "anova" for this, but the anova.sarlm implementation doesn't seem to
permit it straightforwardly. For instance, if I wanted to testing something
