[Mediation-information] Question regarding mediation

[dustin tingley]

Hi Petar-
You'll want to consult this paper, and use the latest version of our
package (4.0, note you need R 2.14 in order to automatically install the
latest version), which has a new function for multiple mediator analysis.
http://imai.princeton.edu/research/medsens.html

best,
Dustin

Dustin Tingley
Government Department
Harvard University
http://scholar.harvard.edu/dtingley
Director, Program on Experience Based Learning in the Social Sciences
http://projects.iq.harvard.edu/peblss/
Contribute to the Research Reservoir:
http://projects.iq.harvard.edu/undergradscholars/pages/research-resources



On Thu, Mar 22, 2012 at 5:02 AM, Petar Milin <pmilin at ff.uns.ac.rs> wrote:

> **
> Dear Prof. Tingley,
> My name is Petar Milin. I am associate professor at the Department of
> Psychology, University of Novi Sad, Serbia. I am lecturing subjects in
> research methodology, mainly, and some parts of cognitive psychology.
> Recently, I started to use your package mediation, and I have one question
> that puzzles me (now in particular, being the fact that I ran onto the
> exact problem, in the real data).
> I haven't much practical experience with the mediation analysis, although
> I read a lot about. Now I am learning you package, which is very
> convenient, very nice.
> In brief, what if there are two mediators M1 and M2 for a certain variable
> X? How can I test this situation?
> I tried following:
> summary(lmM1 <- lm(M1 ~ X, data=dat1))
> summary(lmM2 <- lm(M2 ~ X, data=dat1))
> summary(lmY <- lm(Y ~ M1 + M2 + X, data=dat1))
>
> summary(med1 <- mediate(lmM1, lmY, sims=1000, boot=FALSE,
> treat='X', mediator='M1'))
> #Mediation Effect:  -0.0148 95 % CI  -0.0310410 -0.0001676
>
> summary(med2 <- mediate(lmM2, lmY, sims=1000, boot=FALSE,
> treat='X', mediator='M2'))
> #Mediation Effect:  -0.007471 95 % CI  -0.014932 -0.001934
>
> As you can see, they both seem significant. And medsens shows R^2_M*R^2_Y*
> at which ACME = 0: 0.04 and 0.09, respectively.
>
> Is this correct approach? What would you advice?
>
> I apologize for being direct. Thank you for the understanding.
> Sincerely,
> Petar Milin
>
> #####################################################################################
> Petar Milin
> Department of Psychology, University of Novi Sad, Serbia
> &
> Laboratory for Experimental Psychology, University of Belgrade, Serbia
>
> Address:   Dr Zorana Dindica 2, Novi Sad 21000, Serbia
> E-mail:    pmilin <AT> ff.uns.ac.rs
> Tel.&Fax:  +381 21 458 948
>
> Official homepage (in Serbian):
>
> http://www.ff.uns.ac.rs/fakultet/ljudi/fakultet_odseci_psihologija_petar_milin.html
>
> Personal homepage:
> http://sites.google.com/site/pmilin/
>
> #####################################################################################
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/mediation-information/attachments/20120322/9cd2842b/attachment.html>