R help - Jun 2006 - lm() variance covariance matrix of coefficients.

Hi,

I am running a simple linear model with (say) 5 independent variables. Is
there a simple way of getting the variance-covariance matrix of the
coeffcient estimates?  None of the  values of the lm() seem to provide this.

Thanks in advance,

Ritwik Sinha
rsinha@darwin.cwru.edu
Grad Student
Case Western Reserve University

	[[alternative HTML version deleted]]

summary(object)$cov.unscaled

On Fri, 2 Jun 2006 18:24:57 -0300 (ADT) Rolf Turner wrote:
> summary(object)$cov.unscaled
As the name suggests: this is the unscaled covariance matrix!

Use the vcov() extractor method, i.e.,
  vcov(object)
which has methods not only for "lm" but also many other fitted model
objects.
Z

Peter Dalgaard wrote:
> Rolf Turner <rolf at erdos.math.unb.ca> writes:
> 
> > summary(object)$cov.unscaled
> 
> You need to multiply that with sigma. However, vcov(object) is easier. 
	Well, I thought unscaled meant unscaled --- the plain
	unvarnished covariance matrix!  I figure that multiplying
	the *covariance* matrix by something would be scaling
	it.  Silly me.

	Also:

	(a) Shouldn't that be ``multiply by sigma^2'' rather
	than by sigma?

	(b) Wouldn't it be helpful to have a pointer (``see also'')
	to vcov() in the help on summary.lm()?

				cheers,

					Rolf Turner
					rolf at math.unb.ca