[R] why does R stepAIC keep unsignificant variables?

[S Ellison]

> > Why are the first 5 variables kept in the stepwise result?? 
I don't know, for your data set.

However, AIC is in my limited experience less likely to reject a term than rejection based on p-value at 95% confidence. It's not the same criterion, so there's no immediate reason it should give the same result.

And it often - quite correctly - doesn't.

S Ellison

*******************************************************************
This email and any attachments are confidential. Any use...{{dropped:8}}