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

Re: st: Fw: Multiple mediation

From   John Antonakis <>
Subject   Re: st: Fw: Multiple mediation
Date   Fri, 06 Feb 2009 21:05:54 +0100

Oh, OK (though I wouldn't qualify what you show below as mediation because you are using sureg and not reg3 or 2sls). I'd use it more in this context:

reg3 (z_read z_ses) (z_ses z_write )
testnl [z_ses]z_write*[z_read]z_ses=0 the procedure you show using the delta method to calculate the significance of the indirect path?

Also, how would one bootstrap the SE of the indirect path?


Prof. John Antonakis
Associate Dean
Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny

Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

On 06.02.2009 20:36, Maarten buis wrote:
--- On Fri, 6/2/09, John Antonakis <> wrote:
Do you mean testnl, Maarten?

Yes, my bad.
Also, could you just us how, specifically one would test
for indirect effects in the context of reg3?

*------------------ begin example ----------------------
use, clear
foreach var of varlist read ses write {
	sum `var' if !missing(read,ses,write)
	gen double z_`var' = (`var' - r(mean))/r(sd)
sureg (z_read z_ses) (z_write z_read z_ses)
testnl [z_read]z_ses*[z_write]z_read = 0
nlcom  [z_read]z_ses*[z_write]z_read
*--------------- end example ---------------------------
(For more on how to use examples I sent to the Statalist, see )

-- Maarten

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515

+31 20 5986715

*   For searches and help try:
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index