I ran a hierarchical regression and have a question regarding the results. One of the variables changed from positive in block two to negative in block three (the beta signs). Why would this happen?.

The variable was not significant in either block. I simply would like to know why it changed signs from one block to the next.

  • 1
    $\begingroup$ Maybe you'll find discussion of Simpson's paradox helpful. Here's just one question/answer of probably many that might lead you somewhere useful: stats.stackexchange.com/q/19525/24000 $\endgroup$
    – ndoogan
    Commented Mar 7, 2015 at 4:24

1 Answer 1


Unless all the independent variables are orthogonal to each other, there is no real reason that the signs can't change. When you add variables to the model, you are controlling for those variables. This can do a lot of things. One thing that can happen is mediation. Here's an example:

Dependent variable - amount of damage done by a fire (in, say dollars).

Independent variable 1 - number of fire fighters at the fire.

When you run this, you will get a strong positive relationship - more firefighters, more damage.

Independent variable 2 - size of fire

When you add this to the model, the sign of IV 1 will change (and it could easily go from significant in one direction to significant in the other).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.