Eugene Gallagher <[EMAIL PROTECTED]> wrote: > Rich, > I tend to agree with you about the potential abuse of stepwise > multiple regression. However, it is widely used and I wouldn't label a > study using stepwise as being of necessity flawed, even if the goal was > to evaluate the relative importance of different explanatory variables. > For example, this week's Science has an article that has been widely > reported in the popular press and the key analysis is a stepwise > regression. One way of interpreting the paper is that the authors used > stepwise to make their assessment of the importance of N deposition more > objective. They didn't pick N deposition, the computer did. >
Not having seen the paper, I can't comment on the specifics of the application of stewpise there. But certainly, given the simulation literature on stepwise, the fact that Science published such a paper only shows that they aren't aware of the problems with the procedure. The good intent or reputation of a journal or scientist still won't make the procedure better. In most situations scientists encounter, there isn't "potential abuse", there's just pretty much by definition a badly overfitted model. Mike Babyak . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
