Posted by
Maguin, Eugene on
May 18, 2011; 8:21pm
URL: http://spssx-discussion.165.s1.nabble.com/Really-Easy-Question-about-Mediation-HELP-tp4405692p4407728.html
TBF,
Baron and Kenny's (B&K) work has been superceded by more recent work. A key
name among others is David MacKinnon who is (or was) at Arizona State
University. His website lists his articles. One of the key contributions of
MacKinnon is computing the standard error for the mediated effect. Kris
Preacher is another key name. He has a useful website also.
Given that X is the IV, M is the mediator, and Y is the DV, the B&K
formulation requires, in part, that X->Y, X->M, and M->Y all be significant,
where -> means 'predicts'. And, given X,M->Y, that X->Y=0.
>>1) If I'm wanting to look at mediation of one of my IV effects, would I
enter that variable in by itself in Step 1 as a predictor and leave the
other IV out?
Is step 1 X->Y or X->M? If you leave IV2 out then you should be interested
in testing whether M mediates the relationship between IV1 and the DV.
>>Or can I assess both at the same time by entering both as my
IVs? Or should I just enter the full model (IV1, IV2, IV1*IV2)?
This is testing a different question.
2) If I'm wanting to look at mediation at it pertains to my interaction
term, do it enter the interaction term as the sole predictor in Step 1 or do
I also enter IV1 and IV2 as covariates?
This question has nothing to do with mediation. Entering an interaction term
but leaving out the main effects gives an incorrect estimate for the
interaction term.
What you are wanting to do is not easy because your model is, I think, very
complex. You have two IVs plus their interaction and three possible
mediators. I don't know whether or not you are analyzing each mediator
separately. If you are not analyzing the mediators separately, then you are
talking about 9 possible pathways. You have to use a structural equation
modeling program for something like this. If you are, then an analysis
structured as a multiple regression implies that the effects of IV1, IV2 and
IV1_IV2 all flow through the mediator. Is this what you want? However, this
is also complicated because you have three mediation pathways to test. This
not something that I have done but I'd guess that this also would be better
done in a strucural equation modeling program.
I assume your DV is continuous. If not, that is another issue to contend
with.
Citations (from Cam MacIntosh on Semnet) to look at would include
MacKinnon, D. P., & Fairchild, A. J. (2009). Current directions in mediation
analysis. Current Directions in Psychological Science, 18, 16-20.
MacKinnon, D.P. (2008). Introduction to statistical mediation analysis.
Mahwah, NJ: Erlbaum.
MacKinnon, D. P., Fairchild, A. J., & Fritz, M. S. (2007). Mediation
analysis. Annual Review of Psychology, 58, 593-614.
MacKinnon, D. P., Lockwood, C. M., Hoffman, J. M., West, S. G., & Sheets, V.
(2002). A comparison of methods to test mediation and other intervening
variable effects. Psychological Methods, 7(1), 83-104.
Gene Maguin
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
toph_bei_fong
Sent: Wednesday, May 18, 2011 2:13 AM
To:
[hidden email]
Subject: Really Easy Question about Mediation (HELP!!)
Hi everyone,
I am very, very new to mediation and could use some help. I know the steps
to Baron and Kenny's method but am unsure of how to actually do them in
SPSS.
I have two categorical IVs (which I have dummy coded), the interaction term
of these categorical variables and three continuous mediators.
So, here are my questions:
1) If I'm wanting to look at mediation of one of my IV effects, would I
enter that variable in by itself in Step 1 as a predictor and leave the
other IV out? Or can I assess both at the same time by entering both as my
IVs? Or should I just enter the full model (IV1, IV2, IV1*IV2)?
2) If I'm wanting to look at mediation at it pertains to my interaction
term, do it enter the interaction term as the sole predictor in Step 1 or do
I also enter IV1 and IV2 as covariates?
I just really need someone to walk me through these steps, but after that
I'm golden.
Thank you!
tbf
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD