Hello,
Ma question concerns the logistic regression with binary dependent variable :
If we note the dependent variable Y and the vector of independent variable X
We model in general using SPSS or STATA:
1/ Pr(Y=1合) , we obtain the parameter estimates, if we want to estimate the Pr(Y=0合), this is just 1- Pr(Y=1合)
2/ Now, suppose we estimate Pr(Y=0合), using logistic regression in SPSS or STATA
My question is if the estimate probability of Pr(Y=0合), from a logistic regression which models Pr(Y=1合) using (1), is the same as if we estimate Pr(Y=0合), using logistic regression using (2)
Any suggestions
Thanks
Youss
---------------------------------
How much free photo storage do you get? Store your holiday snaps for FREE with Yahoo! Photos. Get Yahoo! Photos
|