Fisher test or interaction terms to determine if 2 groups are different


I split my sample in 2 groups, participants with condition +M and participants without the condition -M. I calculated correlations and beta coeff( regression by group) so what is the better way to see if these 2 groups differ significantly? the Fischer test for correlations or interaction terms in the regression? Please let me know if I need to provide more details?

Thanks in advance for your help.

PS I am new to this site, how can I give back seeing as I am no expert on stats?


Less is more. Stay pure. Stay poor.
Provide more information!!

What is your dependent variable and how is it formatted?

Fisher's for correlation - not sure that exists?

If you are running a regression, what is this third variables you have not mentioned?

Thanks for wanting to know more. So I am looking at the association/correlation of cortisol (independent) to white blood cells (dependent), and my outcome is the condition M+. So if I look at correlation between cortisol and WBC, it is sig in M- group and non sig in M+ group. But I want to check if it differs between the 2 groups and I thought I would look at Fisher r to Z transformation (I used this I did this and indeed there is a sig diff. I also looked at the regression where I coded it in STATA as: regression WBC cortisol M cortisol*M (covariates) and the interaction term cortisol*M was NOT significant.

Thanks for all your help!


Less is more. Stay pure. Stay poor.
So to paraphrase, you have two independent variables both continuous (cortisol and WBC) in a model predicting a binary condition. You want to know if they interact (multiplicative term). I would just keep them in the model plus their multiplicative interaction term. I would also plot Cortisol by WBC with the sample stratified by binary outcome, and the two lines should not be parallel and could visibly cross.