[R] Step by significance

[Dieter Menne]

Alba wrote:
> 
> Does anybody know how to perform a step function by significance of p
> instead of AIC? I want to perform a forward-backward stepwise logistic
> regression and want to compare the results obtained by steps of
> significance and by steps of AIC.
> 

MASS::dropterm, and play with k. And don't use it other than to play around. 

Dieter


-- 
View this message in context: http://n4.nabble.com/Step-by-significance-tp1754237p1754272.html
Sent from the R help mailing list archive at Nabble.com.