Dear all:
I did the following because I was not sure what a logistic regression
fits ."small.glm" is a glm fit , setting the family to be binomial.
>fitted(small.glm)->p
>log(p/(1-p))->left
> for(i in 1:length(coef(small.glm))){
+ coef(small.glm)[i]*model.matrix(small.glm)[,i]->res[,i]
+ }
> apply(res,1,sum)->right
> plot(left,right) #I got a straight line whose slope was about 1
Therefore ,I am almost sure that what a logistic regression fits is
log(p/(1-p))~b0+b1*x.
Is that right?
Regards,
-----
Best regards,
Bin Yue
*************
student for a Master program in South Botanical Garden , CAS
--
View this message in context:
http://www.nabble.com/what-actually-a-logistic-regression-fits-tf4960618.html#a14207920
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
R-help@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.
