Mallow's Cp Question

Question

When comparing each individually generated model's $C_p$ to the number of parameters, which number of parameters is the comparison to? Each individual model or the overall number of parameters?

Here's an example using R: http://stats.stackexchange.com/questions/8918/is-there-a-way-to-optimize-regression-according-to-a-specific-criterion/8932#8932 — bill_080, Dec 05 '12 at 02:58

score 1 · Answer 1 · edited Dec 05 '12 at 13:38

You compare it to the number of parameters in each individual model. The idea is that for good models, Mallow's $C_p$ is close to the number of parameters, while for poor models it will be much higher. When looking at a large number of models $C_p$ is sometimes plotted against $p$, and then the line $C_p=p$ is drawn in to help with the comparison.

Edit: For an example:
this graph(http://ars.els-cdn.com/content/image/1-s2.0-S0013935106002398-gr1.jpg)
Though they've plotted the line $C_p=p+1$ rather than $C_p=p$.

Mallow's Cp Question

1 Answers1