Hello everyone,
I'm posting a message on the forum because I have a question about interaction coefficients.
In classic regressions I include interaction terms for 3 variables.
The gender of the CFO: takes the value of 1 if it's a woman and 0 otherwise
The gender of the CEO: takes the value of 1 if it is a woman and 0 otherwise
A score: takes a score from 0 to 100.
In my regressions I have coefficients on the following interactions:
CFO gender (woman) * CEO man * SCORE soit 1*0*score
CFO gender (woman) * CEO Woman * SCORE soit 1*1*score
My question is as follows: After thinking about it, I don't understand why I have a coefficient on my first interaction variable (0*0*score). Indeed, if I have 0*0*score I should have my variable at 0 and therefore not necessarily a coefficient. Why do I have a coefficient (which is significant on a few models) and is there any point in keeping this coefficient? Knowing that my question is whether there is an effect of the gender of the CEO when the CFO is a woman.
Thank you very much in advance,
If you need more information to answer my question, please don't hesitate.
I've attached a screen of my results table.
Loïc
I'm posting a message on the forum because I have a question about interaction coefficients.
In classic regressions I include interaction terms for 3 variables.
The gender of the CFO: takes the value of 1 if it's a woman and 0 otherwise
The gender of the CEO: takes the value of 1 if it is a woman and 0 otherwise
A score: takes a score from 0 to 100.
In my regressions I have coefficients on the following interactions:
CFO gender (woman) * CEO man * SCORE soit 1*0*score
CFO gender (woman) * CEO Woman * SCORE soit 1*1*score
My question is as follows: After thinking about it, I don't understand why I have a coefficient on my first interaction variable (0*0*score). Indeed, if I have 0*0*score I should have my variable at 0 and therefore not necessarily a coefficient. Why do I have a coefficient (which is significant on a few models) and is there any point in keeping this coefficient? Knowing that my question is whether there is an effect of the gender of the CEO when the CFO is a woman.
Thank you very much in advance,
If you need more information to answer my question, please don't hesitate.
I've attached a screen of my results table.
Loïc
Comment