1
$\begingroup$

I am going through a model selection process with a mixed-model with 3 variables: A, B, and C. B and C are orthogonal factors. B or C may interact with A, so my full model would be:

fixed:

Y ~ A + B + C + A*B + A*C

random:

~1|D

When I run my analysis, I get four models sharing the lowest AICc.

Y ~ B + A*C
Y ~ A + B + A*C
Y ~ B + C + A*C
Y ~ A + B + C + A*C

I am very confused about what is going on. Obviously there is an interaction between A and C, but how can they all have the same AICc value? Where do I go from here in model selection?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
0
$\begingroup$

So apparently all these formulas are equivalent in R. No matter which model I run, the data summary includes parameters for A, B, C, and A*C. I guess if you have an interaction between A and C, then by default, A and C must be in the model. You learn something new everyday!

Improve this answer
$\endgroup$
1
  • 1
    $\begingroup$ you can add an interaction term in R's lm() without the main effects through writing a:b $\endgroup$
    – Chris Novak
    Apr 19, 2015 at 20:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.