R help - Dec 2006 - extend summary.lm for hccm?

dear R experts:

I wonder whether it is possible to extend the summary method for the
lm function, so that it uses an option "hccm" (well, model
"hc0").  In
my line of work, it is pretty much required in reporting of almost all
linear regressions these days, which means that it would be very nice
not to have to manually library car, then sqrt the diagonal, and
recompute T-stats; instead, I would love to get everything in the same
format as the current output---except errors heteroskedasticity
adjusted.

easy or hard?

regards,

/iaw

On 23 December 2006 at 20:46, ivo welch wrote:
| I wonder whether it is possible to extend the summary method for the
| lm function, so that it uses an option "hccm" (well, model
"hc0").  In
| my line of work, it is pretty much required in reporting of almost all
| linear regressions these days, which means that it would be very nice
| not to have to manually library car, then sqrt the diagonal, and
| recompute T-stats; instead, I would love to get everything in the same
| format as the current output---except errors heteroskedasticity
| adjusted.
| 
| easy or hard?

Did you consider the 'sandwich' package? A simple

	> install.packages("sandwich")
	> library(sandwich)
	> ?vcovHC
	> ?vcovHAC
	
should get you there.

Dirk

-- 
Hell, there are no rules here - we're trying to accomplish something. 
                                                  -- Thomas A. Edison