How to test a moderated mediation model with balanced panel data?

[凌楚定]

Dear list,

 

I think there must be some guys knowledgeable about moderated mediation or mediated moderation.

 

I have read the paper Methods for integrating moderation and mediation: A general analytical framework using moderated path analysis written by Edwards & Lambert (2007) and grasped how to test similar models with general data.

 

However, now my aim is to test a moderated mediation model with balanced panel data. I wonder whether it is still applicable to run the bootstrap macro using SPSS after getting the regression coefficients from STATA, and put the results of bootstrap into Excel to get the confidence interval. I am uncertain about the statistical principles underlying the regressions in SPSS with general data and the regressions in STAT with balanced panel data.

 

I would be grateful if some of you can give me some suggestions. 

---

Chu-Ding LING
Ph.D. Student of Business Administration
School of Management
Zhejiang University

[Ryan]

Install the SPSS custom dialog files for "PROCESS" here:

http://www.afhayes.com/introduction-to-mediation-moderation-and-conditional-process-analysis.html 

Ryan

Sent from my iPhone

On Jun 4, 2014, at 7:08 AM, Chu-Ding LING <[hidden email]> wrote:

Dear list,

 

I think there must be some guys knowledgeable about moderated mediation or mediated moderation.

 

I have read the paper Methods for integrating moderation and mediation: A general analytical framework using moderated path analysis written by Edwards & Lambert (2007) and grasped how to test similar models with general data.

 

However, now my aim is to test a moderated mediation model with balanced panel data. I wonder whether it is still applicable to run the bootstrap macro using SPSS after getting the regression coefficients from STATA, and put the results of bootstrap into Excel to get the confidence interval. I am uncertain about the statistical principles underlying the regressions in SPSS with general data and the regressions in STAT with balanced panel data.

 

I would be grateful if some of you can give me some suggestions. 

---

Chu-Ding LING
Ph.D. Student of Business Administration
School of Management
Zhejiang University

[David Marso]

Why would you need Stata to compute regression coefficients or Excel to get confidence intervals?

凌楚定 wrote

Dear list,
 
I think there must be some guys knowledgeable about moderated mediation or mediated moderation.
 
I have read the paper Methods for integrating moderation and mediation: A general analytical framework using moderated path analysis written by Edwards & Lambert (2007) and grasped how to test similar models with general data.
 
However, now my aim is to test a moderated mediation model with balanced panel data. I wonder whether it is still applicable to run the bootstrap macro using SPSS after getting the regression coefficients from STATA, and put the results of bootstrap into Excel to get the confidence interval. I am uncertain about the statistical principles underlying the regressions in SPSS with general data and the regressions in STAT with balanced panel data.
 
I would be grateful if some of you can give me some suggestions.


Chu-Ding LING
Ph.D. Student of Business Administration
School of Management
Zhejiang University

[凌楚定]

Ryan,

I know PROCESS and used it to test some models before. However, I am confused about how to use it to test a model with panel data. To me knowledge, there is some difference between the estimation of models with panel data and that with general data.

Thanks for your suggestion and hope to get your reply again.

Chu-Ding Ling

2014-06-04 19:31 GMT+08:00 GMAIL <[hidden email]>:

Install the SPSS custom dialog files for "PROCESS" here:

http://www.afhayes.com/introduction-to-mediation-moderation-and-conditional-process-analysis.html 

Ryan

Sent from my iPhone

On Jun 4, 2014, at 7:08 AM, Chu-Ding LING <[hidden email]> wrote:

Dear list,

 

I think there must be some guys knowledgeable about moderated mediation or mediated moderation.

 

I have read the paper Methods for integrating moderation and mediation: A general analytical framework using moderated path analysis written by Edwards & Lambert (2007) and grasped how to test similar models with general data.

 

However, now my aim is to test a moderated mediation model with balanced panel data. I wonder whether it is still applicable to run the bootstrap macro using SPSS after getting the regression coefficients from STATA, and put the results of bootstrap into Excel to get the confidence interval. I am uncertain about the statistical principles underlying the regressions in SPSS with general data and the regressions in STAT with balanced panel data.

 

I would be grateful if some of you can give me some suggestions. 

---

Chu-Ding LING
Ph.D. Student of Business Administration
School of Management
Zhejiang University

[凌楚定]

To me knowledge, there is some difference between the estimation of models with panel data and that with general data. Thus in my opinion it is not appropriate to test panel data model with SPSS, instead I prefer  STATA. However, to obtain the confidence interval of the moderated mediation effects, I think I need to run the SPSS Macro. I am not sure, therefore I raise the question to the list.

Chu-Ding Ling

2014-06-04 20:32 GMT+08:00 David Marso <[hidden email]>:

Why would you need Stata to compute regression coefficients or Excel to get
confidence intervals?


凌楚定 wrote

> Dear list,
>
> I think there must be some guys knowledgeable about moderated mediation or
> mediated moderation.
>
> I have read the paper Methods for integrating moderation and mediation: A
> general analytical framework using moderated path analysis written by
> Edwards & Lambert (2007) and grasped how to test similar models with
> general data.
>
> However, now my aim is to test a moderated mediation model with balanced
> panel data. I wonder whether it is still applicable to run the bootstrap
> macro using SPSS after getting the regression coefficients from STATA, and
> put the results of bootstrap into Excel to get the confidence interval. I
> am uncertain about the statistical principles underlying the regressions
> in SPSS with general data and the regressions in STAT with balanced panel
> data.
>
> I would be grateful if some of you can give me some suggestions.
>
>

> Chu-Ding LING
> Ph.D. Student of Business Administration
> School of Management
> Zhejiang University

-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/How-to-test-a-moderated-mediation-model-with-balanced-panel-data-tp5726324p5726328.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Bruce Weaver]

You may prefer to use Stata for analyzing panel data, but that does not mean it is inappropriate to analyze it with SPSS.  As the following technote suggests, you can use MIXED, GENLIN or GENLINMIXED.  And I suspect you can get SPSS to produce results that are identical (or nearly so) to those from Stata (this may require changing some of the default settings).

   http://www-01.ibm.com/support/docview.wss?uid=swg21479397

HTH.

凌楚定 wrote

To me knowledge, there is some difference between the estimation of models
with panel data and that with general data. Thus in my opinion it is not
appropriate to test panel data model with SPSS, instead I prefer  STATA.
However, to obtain the confidence interval of the moderated mediation
effects, I think I need to run the SPSS Macro. I am not sure, therefore I
raise the question to the list.



Chu-Ding Ling


2014-06-04 20:32 GMT+08:00 David Marso <[hidden email]>:

> Why would you need Stata to compute regression coefficients or Excel to get
> confidence intervals?
>
>
> 凌楚定 wrote
> > Dear list,
> >
> > I think there must be some guys knowledgeable about moderated mediation
> or
> > mediated moderation.
> >
> > I have read the paper Methods for integrating moderation and mediation: A
> > general analytical framework using moderated path analysis written by
> > Edwards & Lambert (2007) and grasped how to test similar models with
> > general data.
> >
> > However, now my aim is to test a moderated mediation model with balanced
> > panel data. I wonder whether it is still applicable to run the bootstrap
> > macro using SPSS after getting the regression coefficients from STATA,
> and
> > put the results of bootstrap into Excel to get the confidence interval. I
> > am uncertain about the statistical principles underlying the regressions
> > in SPSS with general data and the regressions in STAT with balanced panel
> > data.
> >
> > I would be grateful if some of you can give me some suggestions.
> >
> >
> > Chu-Ding LING
> > Ph.D. Student of Business Administration
> > School of Management
> > Zhejiang University
>
>
>
>
>
> -----
> Please reply to the list and not to my personal email.
> Those desiring my consulting or training services please feel free to
> email me.
> ---
> "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos
> ne forte conculcent eas pedibus suis."
> Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in
> abyssum?"
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/How-to-test-a-moderated-mediation-model-with-balanced-panel-data-tp5726324p5726328.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>