[R] ANCOVA with defined error terms

hpdutra hpdutra at yahoo.com
Mon Aug 24 07:27:31 CEST 2009

 When we ran a regular ANOVA we showed that both mice and raccoons respond
positively to cover. So we decided to use raccoons as a co-variate because
those are mouse predators and their presence per se could explain part of
the variation on mice activity. That is the reason why I'm running this
ANCOVA. Thus your model that places coon sequentially first makes more sense
for this question. 

 "Error() model is singular" Some authors claim that one should test for the
interactions of block versus treatment,  to identify any spatial correlation
with the data. That is the reason why I tried to incorporate the
interactions of factors with block in my model. But like you said I don't
have enough degrees of freedom for it. Is there an R function that
calculates the degrees of freedom for complex designs?

I did not understand what you meant by

"Error() notation.  Numerators and Denominators for F tests are
specified indirectly by the relation of the linear subspaces in the
treatment model and the Error model." 

If this is last question is outside the scope of R-help, please just give me
a reference that covers it and I'll do my homework.

Thank you very much Richard, this was wonderful help. 

View this message in context: http://www.nabble.com/ANCOVA-with-defined-error-terms-tp25055311p25110724.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list