(SPSS logistic regression) Variable effect in wrong direction

#1
I am running a logistic regression with 7 IVs, N= 214. The model is significant and the R2 is .45. However, the individual variables show some odd findings and i've not been able to work out a solution...

2 variables are significant, however the relationship (B and ExpB) is in the opposite direction from when i did a bivariate test, also they do not fall in the confidence parameters. Is there anything i can do about this?

Any help would be hugely appreciated!
 

hlsmith

Omega Contributor
#2
Don't use SPSS, but are you sure the procedure has not flipped the variable (e.g., descending/ascending). Perhaps just run the simple regression and check the beta coefficient without any other variables in the model, see if it jives with your bivariate analysis of the IV and DV.
 
#3
Thanks for your reply- I have run the regression with the variables by themselves and they are in the correct direction. However, adding in any other variable switches the direction.