[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
John Antonakis <John.Antonakis@unil.ch> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Mediating variables |

Date |
Mon, 06 Oct 2008 19:25:49 +0200 |

OK....so you could do:

ivreg2 y t (r s = x q)

(if you don't have it type findit ivreg2. It is an extension of the official ivreg STATA command)

If you have panel data you can run:

xtivreg2 y t (r s = x q)

(for fixed-effects only).

Otherwise, xtivreg y t (r s = x q), re

will do the trick if you have random effects.

Problem with the above is if "t" is endogenous then the model is mispecified.

Best,

J.

____________________________________________________

Prof. John Antonakis

Associate Dean Faculty of Business and Economics

University of Lausanne

Internef #618

CH-1015 Lausanne-Dorigny

Switzerland

Tel ++41 (0)21 692-3438

Fax ++41 (0)21 692-3305

http://www.hec.unil.ch/people/jantonakis&cl=en

____________________________________________________

Jaime Gómez wrote:

Thanks John

In fact, looking at my data I have information on one more variable, "q",

that could be used to estimate "r". This variable "q" is directly linked to

"r" in the literature (it is a predictor of "r"), but does not have a direct

relationship with "y". If I understand you correctly, this should allow me

to obtain an estimation for r that could be introduced in my main equation,

perhaps using "ivreg". In any case, I still do not know whether this solves

the problem of not having data on the other two mediators (intuitively, I

imagine that if "s" and "t" are not introduced as mediators, this could

create correlation between the error term of my main equation and the

predictor "x", given that "x" is also a predictor of "s" and "t"). From your

answer, I assume that the panel structure of the data is of no use in this

context. Is that ok?

Thank you very much.

Jaime Gómez

Universidad de Zaragoza

-----Mensaje original-----

De: owner-statalist@hsphsun2.harvard.edu

[mailto:owner-statalist@hsphsun2.harvard.edu] En nombre de John Antonakis

Enviado el: domingo, 05 de octubre de 2008 22:58

Para: statalist@hsphsun2.harvard.edu

Asunto: Re: st: Mediating variables

OK...then just estimate

sureg (y = r s t x) (r s t = x), corr

est store mediators

sureg (y = x) (r s t = x), corr

hausman mediators, equations(1:1)

If the Hausman test is undefined, do it by hand (Wooldridge has the

formulas).

Note: you want tosee if x drops when introducing r s t.

I am just showing you the mechanics of how to run the tests. Again, I would

feel better running a 2sls or reg3 model; but you need to have more

instruments (not just x) to estimate this.

Best,

J.

____________________________________________________

Prof. John Antonakis

Associate Dean Faculty of Business and Economics

University of Lausanne

Internef #618

CH-1015 Lausanne-Dorigny

Switzerland

Tel ++41 (0)21 692-3438

Fax ++41 (0)21 692-3305

http://www.hec.unil.ch/people/jantonakis&cl=en

____________________________________________________

Jaime Gómez wrote:

Thanks for your quick answer."x"

Yes, x predicts three mediators. They, in turn, predict y. Following Baron

and Kenny (1986) I want to see whether the introduction of one of the

mediators ("r") in the equation that expresses the relationship between

and "y" changes the value or the significance of the coefficientequation,

accompanying "x". This is the reason why the predictor ("x") is introduced

in all the equations of the system. Ideally, I would need to introduce the three mediators in my main

but I am only focusing on one of them ("r"). In a paper by Shaver (2005)it

is suggested that 2SLS should be used to account for the correlation amongcan

the errors. My doubts are:

1. I do not know whether omitting the other two mediators ("s" and "t")

cause a problem and, in that case, I am looking for an econometricsolution

2. I have data panel data: on different firms and for different years forestimating

"x", "y" and "r"; I know that Stata gives you the possibility of

an instrumental variables estimation with fixed effects, for example, butI

do not know whether this (or other alternatives) makes sense in thisResearch:

context. In other words, even if 2SLS were the right procedure for

cross-section data, I do not know whether it would be the best alternative

in the presence of panel data

Thanks

Jaime Gómez

Universidad de Zaragoza

Baron, R.M. and Kenny, D.A. (1986) "The moderator-mediator variable

distinction in social psychological research: Conceptual, strategic, and

statistical considerations", Journal of Personality and Social Psychology,

51, 1173-1182

Shaver, J.M. (2005) "Testing for Mediating Variables in Management

Concerns, Implications, and Alternative Strategies", Journal ofManagement,

31 (3), 330-353*

-----Mensaje original-----

De: owner-statalist@hsphsun2.harvard.edu

[mailto:owner-statalist@hsphsun2.harvard.edu] En nombre de John Antonakis

Enviado el: domingo, 05 de octubre de 2008 21:06

Para: statalist@hsphsun2.harvard.edu

Asunto: Re: st: Mediating variables

If I understand your question correctly (from your first sentence), x predicts three mediators, which in term predict y.

This system is not identified for 2sls or 3sls analysis (you need at least as many IVs as you have mediators).

You could estimate it using mvreg or sureg (and then request whether errors are correlated like this):

sureg (y = r s t ) (r s t = x), corr

note: corr will give you a Breusch-Pagan test of independence (for the residuals)--a Hausman test will not help you here.

However, the above is not a strong test.

I am not following what you state regarding the panel structure.

HTH,

John.

____________________________________________________

Prof. John Antonakis

Associate Dean Faculty of Business and Economics

University of Lausanne

Internef #618

CH-1015 Lausanne-Dorigny

Switzerland

Tel ++41 (0)21 692-3438

Fax ++41 (0)21 692-3305

http://www.hec.unil.ch/people/jantonakis&cl=en

____________________________________________________

Jaime Gómez wrote:

Dear Stata usersable

I have a model in which the relationship between a predictor “x” and an

outcome “y” is mediated by three factors (“r”, “s” and “t”). I am only

to test whether one of the predictors (“r”) mediates the relationshipKenny

between “x” and “y” (I only have data on this mediating variable and I

cannot get data on the other two). I would like to implement Baron and

(1986)’s test for mediation. At least, this involves estimating theleast

following system:

Y=a1+b*r+c*x+epsilon1

r=a2+d*x+epsilon2

Given that the errors of the two equations are potentially correlated, it

has been suggested that a 2SLS approach should be used. I have seen that

this could be done with ivregress, provided that I can find data on at

one variable that affects “r” and does not affect “y”. My doubts are thein

following:

1) Given that I have a triangular system, do I have to use the

traditional approach implemented by ivregress or the “modified” proposed

http://www.stata.com/support/faqs/stat/ivr_faq.html ? Are both valid?but

2) How do I test for the hypothesis that the errors are correlated? I

have seen that the use of a Hausman test is suggested in the literature,

I do not know how to implement this in Stata (specially in the case I useinformation

the “modified” approach)

3) Given that I have panel data, could I take advantage of the panel

structure of my data to correct for the fact that I do not have

on two of the mediating variables (“s” and “t”)? Is there a procedure in*

Stata for that?

Thanks a lot Jaime Gómez

Universidad de Zaragoza

*

* 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/

*

* 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/

*

* 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/

**References**:**st: Mediating variables***From:*Jaime Gómez <jaime.gomez@unizar.es>

**Re: st: Mediating variables***From:*John Antonakis <John.Antonakis@unil.ch>

**RE: st: Mediating variables***From:*Jaime Gómez <jaime.gomez@unizar.es>

**Re: st: Mediating variables***From:*John Antonakis <John.Antonakis@unil.ch>

**RE: st: Mediating variables***From:*Jaime Gómez <jaime.gomez@unizar.es>

- Prev by Date:
**st: outreg, outreg2, and the thread-jacking** - Next by Date:
**RE: st: reporting cox regression for ordinal variables** - Previous by thread:
**RE: st: Mediating variables** - Next by thread:
**Re: st: Mediating variables** - Index(es):

© Copyright 1996–2023 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |