[R] binomial GLM quasi separation

[lincoln]

#Uwe:

I have realized that in the firstly linked post ( 
http://r.789695.n4.nabble.com/OT-quasi-separation-in-a-logistic-GLM-td875726.html#a3850331
OT-quasi-separation-in-a-logistic-GLM  ) I have told something misleading:
in fact my independent variables are not log-normally distributed since
there are lot of zeros that constitute the more frequent values. I have not
been able to normalize them: I don't even  know if it is possible to do it.
For the assumption of normally distributed predictors I believe I can't use
a lda.

#Gavin:

I have read carefully your thread but I am not sure to understand what you
are suggesting (my gaps in statistics!). You say that it should be due to
the /Hauck Donner/ effect and that it is not a quasi separation or
separation issue. Even though, I am still unsure to understand why I found
such a high asymptotic standard error.

Anyway, how should I consider this result? Should I find another way to
analyze this process or I could consider this as correct?

If I am understanding this enough, this warning message and the very high
estimates should be due to  /Hauck-Donner/. Regarding that reference to
Venables and Ripley (2002) on this issue, I have found this ( 
http://kups.ku.edu/maillist/classes/ps707/2005/msg00023.html Hauck-Donner  )
where it is said that "The practical advice, then, is to run the model with
all of the variables, and then run again with the questionable one removed,
and conduct a likelihood ratio test./ and I suppose that the p-values for
hcp should be the LRT p-value, isn't it?

Thanks for taking your time to help me in this.

Simone




--
View this message in context: http://r.789695.n4.nabble.com/binomial-GLM-quasi-separation-tp3901687p3907716.html
Sent from the R help mailing list archive at Nabble.com.