<div>Thanks so much for the response. To delve a little further, what I'd really like to do is say what the total effect of the mediator is. To further sketch out the scenario:</div><div><br></div><div>M = b1_treatment*T</div>
<div>Y = b_mediator*M + b2_treatment*T</div><div>Y = b_treatment*T</div><div>b_treatment = ATE = direct eff + indirect eff</div><div><br></div><div>I get all of that. What I'm unclear about is how I can interpret the indirect effect in conjunction with b_mediator. Could I say something like "the effect of the mediator is (indirect effect + b_mediator) per unit mediator" or is the indirect effect already accounted for in b_mediator? Or is the situation more like:</div>
<div><br></div><div>total effect of mediator = (1-p)indirect_effect + b_mediator</div><div>b_mediator = p*indirect_effect + independent effect of mediator</div><div><br></div><div>In substantive terms, I'm not only interested in the effect of the treatment but that of the mediator.</div>
<br><div class="gmail_quote">On Tue, Nov 22, 2011 at 5:58 AM, Kosuke Imai <span dir="ltr"><<a href="mailto:kimai@princeton.edu">kimai@princeton.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Hi Daniel,<br>
<br>
If you regress Y on the treatment (but not the mediator), then you will get the average total effect which equals the sum of direct and indirect effect.<br>
<br>
Kosuke<br>
<br>
Department of Politics<br>
Princeton University<br>
<a href="http://imai.princeton.edu" target="_blank">http://imai.princeton.edu</a><br>
<div class="HOEnZb"><div class="h5"><br>
<br>
On Nov 22, 2011, at 5:18 AM, Daniel Lim wrote:<br>
<br>
> Dear Professor Imai, I'm a poli sci PhD student at UCLA and I'm currently working on a paper involving your mediational model. I had a quick question regarding the interpretation of results:<br>
><br>
> Say that we are looking at the following linear models:<br>
> M = b1_treatment*T<br>
> Y = b_mediator*M + b2_treatment*T<br>
> In a nonmediational setting, we would interpret the effect of the mediator as b_mediator per unit M.<br>
><br>
> When we apply "mediate" to the above, we get a result like the following:<br>
> Mediation Effect: X<br>
> Direct Effect: Y<br>
> Total effect X+Y<br>
> How do we interpret this result in conjunction with the original outcome model? Is X additive with b_mediator or does it supplant that result? In other words, are we saying b2_treatment=X+Y or b2_treatment+b2_mediator=X+Y (or are both these interpretations completely off)?<br>
><br>
> Thanks,<br>
> --<br>
> Daniel Lim<br>
> PhD Student<br>
> Dept of Political Science, UCLA<br>
> <a href="mailto:daniel.k.lim@gmail.com">daniel.k.lim@gmail.com</a><br>
> <a href="tel:818-480-2679" value="+18184802679">818-480-2679</a> (USA)<br>
><br>
><br>
<br>
<br>
<br>
</div></div></blockquote></div><br><br clear="all"><div><br></div>-- <br>Daniel Lim<div>PhD Student</div><div>Dept of Political Science, UCLA</div><div><a href="mailto:daniel.k.lim@gmail.com" target="_blank">daniel.k.lim@gmail.com</a></div>
<div>818-480-2679 (USA)</div><div><br></div><br>