Process 4: Model 2

[Salbod]

Happy Wednesday,

Did I correctly generate the data points to graph a two-way interaction from Process 4’s Model 2 output?  

A discussion of Model 2: Additive Moderation can be found in Hayes, A. F. (2022). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach. Guilford publications (pp 337-346).

The plots that Hayes’ Model 2 generates aren’t clear.

Data was centered. Assume all predictors are continuous. Predictor values for X and Mod1 will be: -SD, M=0, and +SD.

Can the second moderator be set to its mean and the data points for the graph of the Mod1 with X be generated using only the coefficients of X, Mod1, and their interaction?

Coeffs:
Model
                 coeff         se          t          p       LLCI       ULCI
constant     4.4748      .3286    13.6193      .0000     3.8299     5.1198
X                .1154      .0846     1.3651      .1726     -.0506      .2814
Mod1          -.8449      .2006    -4.2124      .0000    -1.2386     -.4512
Int_1           .2208      .0518     4.2611      .0000      .1191      .3225
Mod2          -.0241      .0062    -3.8655      .0001     -.0364     -.0119
Int_2           .0054      .0016     3.3221      .0009      .0022      .0086


X * Mod1 (at the mean for Mod2)
Low-Low Data point = 4.47 + (.12*-SDx)+(-.84*-SDm1)+(.22*-SDx*-SDm1)
Med-Low Data point = 4.47 + (.12*Mx=0)+(-.84*-SDm1)+(.22*0*-SDm1)
High-High Data point = 4.47 + (.12*+SDx)+(-.84*+SDm1)+(.22*+SDx*+SDm1)

I will appreciate any suggestions. Thanks, Steve  

[Bruce Weaver]

You could always check your results by using REGRESSION with OUTFILE and then APPLYMODEL.  

https://stats.stackexchange.com/questions/20680/how-to-import-and-run-a-model-with-spss
https://www.youtube.com/watch?v=eboTREc3uSk

The YouTube video shows how to use APPLYMODEL following logistic regression, but it should help you understand how to use it following linear regression too.  

HTH.

Salbod wrote

Happy Wednesday,

Did I correctly generate the data points to graph a two-way interaction from Process 4’s Model 2 output?  

A discussion of Model 2: Additive Moderation can be found in Hayes, A. F. (2022). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach. Guilford publications (pp 337-346).

The plots that Hayes’ Model 2 generates aren’t clear.

Data was centered. Assume all predictors are continuous. Predictor values for X and Mod1 will be: -SD, M=0, and +SD.

Can the second moderator be set to its mean and the data points for the graph of the Mod1 with X be generated using only the coefficients of X, Mod1, and their interaction?

Coeffs:
Model
                 coeff         se          t          p       LLCI       ULCI
constant     4.4748      .3286    13.6193      .0000     3.8299     5.1198
X                .1154      .0846     1.3651      .1726     -.0506      .2814
Mod1          -.8449      .2006    -4.2124      .0000    -1.2386     -.4512
Int_1           .2208      .0518     4.2611      .0000      .1191      .3225
Mod2          -.0241      .0062    -3.8655      .0001     -.0364     -.0119
Int_2           .0054      .0016     3.3221      .0009      .0022      .0086


X * Mod1 (at the mean for Mod2)
Low-Low Data point = 4.47 + (.12*-SDx)+(-.84*-SDm1)+(.22*-SDx*-SDm1)
Med-Low Data point = 4.47 + (.12*Mx=0)+(-.84*-SDm1)+(.22*0*-SDm1)
High-High Data point = 4.47 + (.12*+SDx)+(-.84*+SDm1)+(.22*+SDx*+SDm1)

I will appreciate any suggestions. Thanks, Steve

[Salbod]

Bruce, thank you for the help. I will follow your suggestions to the letter. --Steve

PS I love videoes.