R help - Apr 2012 - Error: (subscript) logical subscript too long

Hello, 

I am trying to perform a logistic regression using counts. For example:

cedegren <-
read.table("http://www.cloudstat.org/index.php?do=/attachment/download/id_95
/", header=T)
attach(cedegren)
ced.del <- cbind(sDel, sNoDel)
ced.logr <- glm(ced.del ~ cat + follows + factor(class),
family=binomial("logit"))

This works. However, if I change the family to Gaussian:

ced.logr <- glm(ced.del ~ cat + follows + factor(class), family=gaussian)

I get the error:
Error: (subscript) logical subscript too long

I would like to use the probit function. Is this possible?

Best regards, 
Ioanna

On 2012-04-02 08:52, IOANNA wrote:
> Hello,
>
> I am trying to perform a logistic regression using counts. For example:
>
> cedegren<-
>
read.table("http://www.cloudstat.org/index.php?do=/attachment/download/id_95
> /", header=T)
> attach(cedegren)
> ced.del<- cbind(sDel, sNoDel)
> ced.logr<- glm(ced.del ~ cat + follows + factor(class),
> family=binomial("logit"))
>
> This works. However, if I change the family to Gaussian:
>
> ced.logr<- glm(ced.del ~ cat + follows + factor(class), family=gaussian)
>
> I get the error:
> Error: (subscript) logical subscript too long
>
> I would like to use the probit function. Is this possible?
I think that you don't understand the 'family=' argument in glm
(nor,
perhaps, generalized linear models as such).

Hint: check ?family.

Peter Ehlers
>
> Best regards,
> Ioanna
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.