Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: moderated mediation logistic outcome


From   Cameron McIntosh <[email protected]>
To   STATA LIST <[email protected]>
Subject   RE: st: moderated mediation logistic outcome
Date   Fri, 28 Oct 2011 11:37:32 -0400

Tobias,
I don't know about the precise Stata code for estimating a mod-med model, but I would caution you that if you are using a series of logistic regression steps to test for the presence of moderated mediation, you will need to account for the fact that the variance of the outcome depends on the model (and will change across equations as predictors and interactions terms are added) -- all this due to the identification constraint that error = pi-squared/3 = 3.29. This also means that coefficients will be recaled to respect the constraint, and will thus need to be standardized to allow for comparisons across equations. Note that the same issue applies to the probit case with error = 1.0. You may wish to see:
Buis, M.L. (2010). Direct and indirect effects in a logit model. The Stata Journal, 10(1), 11–29.https://teamsite.smu.edu.sg/wiki/stats/Shared%20Documents/Stata%20Journals/2010/sj10-1.pdf
MacKinnon, D. P., & Dwyer, J. H. (1993). Estimating mediated effects in prevention studies. Evaluation Review, 17, 144-158.
MacKinnon, D.P., Lockwood, C.M., Brown, C.H., Wang, W., & Hoffman, J.M. (2007). The intermediate endpoint effect in logistic and probit regression. Clinical Trials, 4(5), 499-513.http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2857773/pdf/nihms-173365.pdf
Li, Y, Schneider, J.A., & Bennett, D.A. (2007). Estimation of the mediation effect with a binary mediator. Statistics in Medicine,  26(18), 3398-3414.
Jasti, S., Dudley, W.N., & Goldwater, E. (2008). SAS macros for testing statistical mediation in data with binary mediators or outcomes. Nursing Research, 57(2), 118-122.
Eshima, N., Tabata, M., & Zhi, G. (2001). Path analysis with logistic regression models: effect analysis of fully recursive causal systems of categorical variables. Journal of the Japanese Statistical Society, 31(1), 1-14. http://www.scipress.org/journals/jjss/pdf/3101/31010001.pdf
Huang, B., Sivaganesan, S., Succop, P., & Goodman, E. (2004). Statistical assessment of mediational effects for logistic mediational models. Statistics in Medicine, 23(17), 2713–2728.
Cam
> Date: Fri, 28 Oct 2011 09:15:21 +0100
> Subject: Re: st: moderated mediation logistic outcome
> From: [email protected]
> To: [email protected]
> 
> That's not an exact equivalent, as it treats missings in -usepurchase-
> differently, but is more likely to be what is wanted if any missings
> exist.
> 
> On Fri, Oct 28, 2011 at 9:09 AM, Nick Cox <[email protected]> wrote:
> > Sorry, no idea on your main question. Just a comment that
> >
> >        generate switch    = .
> >        replace  switch = 0 if (usepurchase <= 1)
> >        replace  switch = 1 if (usepurchase >= 2)
> >        rename switch y  /* dependent variable   */
> >
> > can be rewritten as one line
> >
> >       gen y = usepurchase >= 2 if usepurchase < .
> >
> > Nick
> >
> > On Fri, Oct 28, 2011 at 8:57 AM, Tobias Schlager
> > <[email protected]> wrote:
> >> Dear List
> >>
> >> I am encountering a problem with moderated mediation. I wanted to use
> >> moderated mediation as in the link below specified by Preacher et al.,
> >> however, my dependent variable is binary.
> >> For this, I was trying to implement a logistic regression, however, I am
> >> not sure about the correct specification, because from what I know sureg
> >> is only for linear regression.
> >>
> >> Here is my specification which relates to model 1 of the link below:
> >>        use "x.dta", clear
> >>        generate switch    = .
> >>        replace  switch = 0 if (usepurchase <= 1)
> >>        replace  switch = 1 if (usepurchase >= 2)
> >>        rename switch y  /* dependent variable   */
> >>        rename satis x     /* independent variable */
> >>        rename dbpu m     /* mediator variable    */
> >>        quietly summarize x
> >>        global m=r(mean)
> >>        global s=r(sd)
> >>        generate mx=m*x  /*  mv by iv interaction */
> >>        sureg (m x)(y m x mx)
> >>
> >> It would be great if anybody knew how to do this. Thanks a lot,
> >> Tobias
> >>
> >>
> >> http://www.ats.ucla.edu/stat/stata/faq/modmed.htm#model1
> >
> 
> *
> *   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index