R help - Mar 2004 - performing type III

Hi,

I meet some tecnhical problem when performing type III test in an 
analysis of covariance.
I code with contrast=sum and precise type="III" for the anova table.
There is a warning message like this:
Models with response "NULL" removed and type I is performed by
default.
And R-Help is not very clear on use of contrasts.

Please don't rush in the usual holy war about this topic. And if 
somebody as a concrete example...

Thank you

Alex

	[[alternative HTML version deleted]]

Dear Alex,

The anova() function doesn't take a type argument, producing the error.
Perhaps the Anova() function in the car package will do what you want.

I hope that this helps,
 John 
> -----Original Message-----
> From: r-help-bounces at stat.math.ethz.ch 
> [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Hardouin Lo?c
> Sent: Wednesday, March 10, 2004 10:16 AM
> To: R-help at stat.math.ethz.ch
> Subject: [R] performing type III
> 
> Hi,
> 
> I meet some tecnhical problem when performing type III test 
> in an analysis of covariance.
> I code with contrast=sum and precise type="III" for the anova
table.
> There is a warning message like this:
> Models with response "NULL" removed and type I is performed 
> by default. 
> And R-Help is not very clear on use of contrasts.
> 
> Please don't rush in the usual holy war about this topic. And 
> if somebody as a concrete example...
> 
> Thank you
> 
> Alex
>