Re: Re: st: What is the effect of centering on marginal effects?

[Christopher Baum <kit.baum@bc.edu>]

<>
On Aug 2, 2012, at 2:33 AM, Alessandro wrote:

> Centered and uncentered models are algebraically equivalent (see
> Brambor et al, "Understanding Interaction Models: Improving Empirical
> Analyses" 2006). The only difference is that, in an uncentered model,
> the coefficient of b1 corresponds to the marginal effect of a one unit
> change in X when the conditioning variable Z is zero, while the
> corresponding coefficient on the centered model gives you the marginal
> effect of a change in X when Z is at its mean.
> 
> This means that centering variables will not reduce multicollinearity
> on your model.

I don't think this is quite true. See what happens to the VIF when the interacted variables are centered. Also note that the elasticity
estimates change, and become very imprecise with centering.

sysuse auto, clear
qui reg price length weight c.length#c.weight
estat vif
margins, eyex(_all) 
// center from SSC (Jann)
center price length weight
qui reg c_price c_length c_weight c.c_length#c.c_weight
estat vif
margins, eyex(_all) 

Kit


Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                             An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
  An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/