R help - Apr 2009 - re siduals

Hi All,

I am trying to fit a linear regression between the tool speed and the tool
type ( type A, Type B , Type C) where the response is the tool speed and the
regressor is the tool type.

I introduced two dummy variables X1 and X2  as follows

             X1  X2
Tool A   0   0
Tool B   0   1
Tool C   1    0


Model<-Lm (y~X1+X2)

My question is on the residual plot, it looks like three cluster because  I
have three tool types. Is such a plot is ok with the constant variance
assumption  and normality (below is a link for the plot)?I have never seen
such a plot of the residuals


http://www.nabble.com/file/p22972254/question.JPG question.JPG 
-- 
View this message in context:
http://www.nabble.com/residuals-tp22972254p22972254.html
Sent from the R help mailing list archive at Nabble.com.