Re: st: binary_mediation

[Bo MacInnis <bo@macinnis.org>]

Hi,

I have good news to report.

Phil Ender, author of -binary_mediation_ program, contacted me in 
private and generously offered to help.

Phil has updated -binary_mediation_ program, now version 2.1, and it's 
available for downloading through -findit-. Users can access the 
standardized/rescaled a coefficients and b coefficients through the 
following returns:

mat list r(mat_a)
mat list r(mat_b)

This new functionality works wonder and solves my problem.

A load of thank-you to you, Phil!!!

Bo

On 2/15/2011 5:42 PM, Bo MacInnis wrote:
> Hi, Statalisters,
>
> I'm trying to use the wonderful program binary_mediation for my analysis
> where all the variables (IV, mediators, and DV) are dichotomous.
>
> In the past, I posted a question and got excellent responses from Phil
> Ender and Maarten Buis:
>
> http://www.stata.com/statalist/archive/2010-08/msg00011.html
> http://www.stata.com/statalist/archive/2010-08/msg00013.html
>
> I am wishfully thinking that it would be so wonderful if
> binary_mediation would produce the values of a1 and b1 (and a2 and b2
> etc) in addition to the current list of outputs (such as indir1, indir2,
> etc), because I'd like to plot the values for the sides of the typical
> media triangle where values a1/b1 are plotted separately.
>
> I have  calculated a1/b1 based the spreadsheet provided by N. Herr
> http://nrherr.bol.ucla.edu/Mediation/logmed.html  .
>
> I also have multiple (dichotomous) mediators for which I will need the
> values of a1/b1, a2/b2, and a3/b3, and N. Herr's spreadsheet assumes one
> mediator. I could probably extend the formula to include multiple
> mediators, but it would be awfully nice if someone who is expert on this
> has already done so.
>
> It is just my wish. I am grateful for the binary_mediation program.
> Since binary_mediation must calculate a1/b1 etc, I thought it would be
> really nice if it would output these values.
>
> Thank you,
> Bo MacInnis
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/