[R] Problem comparing logistic regression output with SPSS.
Ravi Kulkarni
ravi.kulk at gmail.com
Mon Mar 29 08:56:06 CEST 2010
Hello,
I have a logistic regression model
contrasts(z) = contr.helmert(4)
mylogit = glm(binvar~x+y+z,
family=binomial("logit"))
summary(mylogit)
where x is a ratio variable, y is categorical with two levels, z is
categorical with 4 levels.
SPSS gives me the same values for the coefficients as R for x and y. But
those for z and the intercept are different. (I did use the Helmert contrast
in SPSS too.)
Is there some other parameter I need to specify in the model? The method
of entering variables in the model? Is that what is causing the difference?
Thanks,
Ravi Kulkarni
--
View this message in context: http://n4.nabble.com/Problem-comparing-logistic-regression-output-with-SPSS-tp1694767p1694767.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help
mailing list