[R-sig-ME] sandwich variance estimation using glmer?

Rolf Turner r.turner at auckland.ac.nz
Wed Nov 3 23:27:00 CET 2010

On 4/11/2010, at 10:49 AM, Andrew Robinson wrote:


> .......  If the functionality that you want isn't there, it's
> because noone else has wanted it badly enough to
> a) code it up, or
> b) pay someone else to code it up.


There is another possibility that should be taken into consideration.
The person wanting that functionality may lack both the requisite skills
and insight to code up the functionality his or herself and the financial
resources to pay someone else to do this.

Yet another possibility is that the person responsible for the original
code simply never thought of including the requested functionality.  I am
sure I've seen instances where people have asked (on the R-help list) for
features in specific packages, and the maintainers of those packages have
responded ``Yes, that's a good idea.  I'll include that in the next release.''
Can't give specific examples off the top of my head.  However I know for
certain that I have accommodated such feature requests from users in respect
of packages that I maintain (specifically Iso and deldir).


		Rolf Turner

More information about the R-sig-mixed-models mailing list