[Rd] Re: [R] H-F corr.: covariance matrix for interaction effect

From: Bela Bauer <bela_b_at_gmx.net>
Date: Tue 01 Mar 2005 - 11:27:36 GMT

Peter Dalgaard wrote:
> Just in case anyone was wondering, I think I now know what SAS is
> doing, and yes, it is a bug.

I was still wondering. :-)
Now, this is quite some interesting news, since everyone here has been relying on SAS H-F corrections, and I don't think they'll be amused to know that they might've been wrong.

I've been glancing over to Rd, but I didn't see anything about it - do you have any code yet that I could look at to figure out what you do? It doesn't need to be complete yet, just something that will tell me about the algorithm...



R-devel@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel Received on Tue Mar 01 22:29:29 2005

This archive was generated by hypermail 2.1.8 : Mon 20 Feb 2006 - 03:21:01 GMT