R help - Sep 2011 - Question about model selection for glm -- how to select features based on BIC?

Hi All, 
After fitting a model with glm function, I would like to do the model selection
and select some of the features and I am using the "step function" as
follows:
 glm.fit <- glm (Y ~ . , data = dat, family =
binomial(link=logit)) AIC_fitted = step(glm.fit, direction = "both")
I was wondering is there any way to select the features based on BIC rather than
AIC? is there any other function that I should use?
Thanks a lot,Andra

	[[alternative HTML version deleted]]

If you read the help file on the step() function
     ?step
you will see a reference to BIC under the description of the k= argument.

This suggests that you could try:
     BIC.fitted = step(glm.fit, k=log(dim(dat)[1]))

Jean


Andra Isan wrote on 09/07/2011 06:12:19 PM:
> 
> Hi All, 
> After fitting a model with glm function, I would like to do the 
> model selection and select some of the features and I am using the 
> "step function" as follows:
>  glm.fit <- glm (Y ~ . , data = dat, family = binomial
> (link=logit)) AIC_fitted = step(glm.fit, direction = "both")
> I was wondering is there any way to select the features based on BIC
> rather than AIC? is there any other function that I should use?
> Thanks a lot,Andra
> 
	[[alternative HTML version deleted]]