R help - Jan 2005 - problem with fitted probability in glm

Good morning,

Sorry to disturb you.

I have a set of variable (not correlated) and with a stepwise selection
procedure (step) on my multiple glm I obtain a result but with a warning message
saying:

fitted probabilities numerically 0 or 1 occurred in: glm.fit(x[, jj, drop
FALSE], y, wt, offset = object$offset,

I try to understand what it means without success. Could you help me?

Thanks

Flavio Zanini

http://finzi.psych.upenn.edu/R/Rhelp02a/archive/29712.html
This was the first message that I came across when searching the archives. From
my limited experience I would think that you need to understand what you are
doing rather than what R is doing. As the message explains R is flagging issues
with your data.

Tom
> -----Original Message-----
> From: flavio.zanini at epfl.ch [mailto:flavio.zanini at epfl.ch]
> Sent: Tuesday, 11 January 2005 1:50 PM
> To: r-help at stat.math.ethz.ch
> Subject: [R] problem with fitted probability in glm
> 
> 
> Good morning,
> 
> Sorry to disturb you.
> 
> I have a set of variable (not correlated) and with a stepwise 
> selection
> procedure (step) on my multiple glm I obtain a result but 
> with a warning message
> saying:
> 
> fitted probabilities numerically 0 or 1 occurred in: 
> glm.fit(x[, jj, drop > FALSE], y, wt, offset = object$offset,
> 
> I try to understand what it means without success. Could you help me?
> 
> Thanks
> 
> Flavio Zanini
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html
>