hierarchical multiple regression


New Member
Hi guys,

I'm pretty clueless when it comes to stats, so I was wondering if you could help.
I'm testing 2 competing theories on personality causes of bulimia. One says that two types of impulsiveness (reward drive and rash impulsivity) strongly predict food craving. Another says that rash impulsivity predicts food craving only when in a negative mood (aka urgency)

So I manipulated mood, so that some where induced into a negative mood and others in a neutral mood. I have measures of rash impulsivity, reward drive and food craving.

Now... to test these theories, would it makes sense to do a hierarchical multiple regression, with rash impulsivity and reward drive at step one and an interaction between mood and rash impulsivity at step 2?

Would that work? Do I need to test mood as well in the first step?

Sorry it's a bit confusing, but any help would be appreciated.
Thanks :)