> From: [EMAIL PROTECTED] (Sylvia J. Hysong, Ph.D.)
> Organization: http://groups.google.com/
> Newsgroups: sci.stat.edu,comp.soft-sys.stat.spss
> Date: 5 Jul 2001 14:35:24 -0700
> Subject: Double mediation
>
> Hello,
>
> I'm hoping someone can help me with this. I have looked at a
> multitude of resources including the David Kenny page, this and other
> newsgroups, Pedhazur (1982), Cohen & Cohen (1983), and Darlington
> (1990?), to no avail. I am hoping someone can direct me to the right
> resource. I am trying to conduct a test of double mediation. In
> other words, I am trying to test the hypothesis that x-->z1-->z2-->y.
> Is there a way to do this (and if so, what is it?), or must I result
> to a path analysis or a structural equation model?
>
> Thanks in advance for any help.
Would this do it?
Estimate a regression model with y as the dependent and x, z1 and z2 as
independents. That gives the direct path from z2-->y, controlling for x and
z1.
Then a second model with z2 as the dependent and x, and z1 as independents.
That gives the direct path from z1-->z2, controlling for x.
The a third model with z1 as the dependent and x as the independent.
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
