Could someone with a degree in Stats please help
Hi! Really not the place to be asking this, but worth a shot. Apologies if I sound really stupid.
I'm really confused about what regression to run if I have multiple treatments administered in multiple ways. For instance, if I want to look at the impact of two different kinds of messages on turnout, but each message is administered as: 1) only to the women in the house 2) only to the men 3) to the men and women separately 4) to the men and women together. How should I frame the regression equation?
Would it be:
Turnout=β0 + β1×Message1+ β2×Message2+ 𝛽3×WomenOnly + 𝛽4×MenOnly + 𝛽5×MenWomenSeparate + 𝛽6×MenWomenTogether + ControlVariables+𝜖
Where all indep variables are dummy variables
Edit: haha thanks for the responses guys, didn't expect any. Yes I'm pretty sure what I did is wrong! Figured I need to look at the interaction between a treatment and method variable. Thank you!
=14.5
I don't think you're correct. Consider the variables Men Only and Women Only. They are not independent (we cannot send the message to men only AND women only at the same time). They are dependent and should therefore be represented by one variable. This dependence is also true of some other variables in your equation. If two variables are related somehow, they cannot be independent variables. Hope that makes sense.
Not quite sure what the proper way to do this is because I don't understand the problem fully, but I think your setup is wrong.
Ask your professor during office hours.
Molestiae sapiente qui ex magni voluptas. Id illo consequuntur ut quam numquam. Voluptas consectetur eos veritatis facilis possimus omnis qui. Nihil animi nihil quod et. Modi provident pariatur et incidunt ullam. Accusamus dolor a quia nihil dolorem. Reiciendis ea eligendi alias placeat earum deleniti.
See All Comments - 100% Free
WSO depends on everyone being able to pitch in when they know something. Unlock with your email and get bonus: 6 financial modeling lessons free ($199 value)
or Unlock with your social account...