Using the PROCESS Macro in SPSS

Post date: Nov 26, 2014 5:7:9 PM

Drawn from:

Hayes, Andrew F. (2013-04-22). Introduction to Mediation, Moderation, and Conditional Process Analysis: Methodology in the Social Sciences (Page 423). Guilford Press. Kindle Edition.

How to Install as a Macro

PROCESS can be used as either a command-driven macro or installed as a custom dialog for setting up the model using SPSS’s point-and-click user interface. When executed as a macro, the PROCESS.sps file should first be opened as a syntax file. Once it has been opened, execute the entire file exactly as is. (Highlight everything, then press the Go button).

Once the PROCESS.sps program has been executed, it can be closed and the PROCESS command is available for use in any SPSS program. Running PROCESS.sps activates the macro, and it will remain active so long as SPSS remains open. The PROCESS file must be loaded and reexecuted each time SPSS is opened in order to use the features of the PROCESS command. See the “Examples” section starting on page 422 for how to set up a PROCESS command in a syntax window. Please also read “Model Designation and Estimation” (page 426) and the “Notes” section (page 439) for important details pertinent to execution, including calling PROCESS with the SPSS INSERT command.

Syntax

process vars=varlist/y=yvar/x=xvar/m=mvlist/model=num

[/w= wvar] [/z=zvar]

[/v= vvar] [/q=qvar]

[/wmodval= wval]

[/zmodval= zval]

[/vmodval= vval]

[/qmodval= qval]

[/mmodval= mval]

[/xmodval= xval]

[/cluster= clvar]

[/contrast=(0**)(1)]

[/boot= z(1000**)]

[/mc= g(0**)]

[/conf= ci(95**)]

[/effsize=(0**)(1)]

[/normal=(0**)(1)]

[/jn=(0**)(1)]

[/coeffci=(0)(1**)]

[/varorder= vord(2**)]

[/hc3=(0**)(1)]

[/covmy= cov(0**)]

[/total=(0**)(1)]

[/center=(0**)(1)]

[/quantile=(0**)(1)]

[/detail=(0)(1**)]

[/plot=(0**)(1)]

[/seed= sd]

[/percent=(0**)(1)]

[/iterate= it(10000**)]

[/converge= cvg(.00000001)]

[/save=(0**)(1)].

Usage Examples

(1) Simple Moderation

process vars=newlaws alcohol concerns use age/y=newlaws/x=alcohol/m=concerns/model=1/quantile=1/center=1/plot=1/jn=1.

  • Estimates a simple moderation model with the effect of alcohol on newlaws moderated by concerns.

  • use and age are included in the model as covariates.

  • alcohol and concerns are mean centered prior to analysis.

  • Generates the conditional effects of alcohol on newlaws at values of concerns equal to the 10th , 25th, 50th, 75th, and 90th percentiles of the distribution in the sample.

  • Produces a table of estimated values of newlaws for various values of alcohol and concerns.

  • Implements the Johnson–Neyman technique to identify the values on the continuum of concerns at which point the effect of alcohol on newlaws transitions between statistically significant and nonsignificant at the .05 level.

(2) Moderated Moderation

process vars=mathprob gender explms treat/y=mathrpob/x=treat/m=explms/w=gender/model=3/mmodval=4.

  • Estimates a moderated moderation model predicting mathprob from treat while including a three-way interaction between treat, explms, and gender in the model along with all required two-way interactions.

  • Generates the conditional effect of treat on mathprob for both males and females when explms = 4.

(3) Simple Mediation

process vars=donate winner votes/y=votes/x=donate/m=winner/model=4/total=1/effsize=1/boot=10000.

  • Estimates the total and direct effect of donate on votes, as well as the indirect effect of donate on votes through winner.

  • Generates a bias-corrected 95% bootstrap confidence interval for the indirect effect using 10,000 bootstrap samples.

  • Produces point estimates and bias-corrected 95% bootstrap confidence interval estimates of various indices of effect size for the indirect effect.

(4) Parallel Multiple Mediation

process vars=know educ attn elab sex age/y=know/x=educ/m=attn elab /model=4//contrast=1/normal=1/conf=90/save=1.

  • Estimates the direct effect of educ on know, as well as the total and specific indirect effects of educ on know through attn and elab, with

  • attn and elab functioning as parallel mediators. sex and age are included in the model as covariates.

  • Produces the Sobel test for the specific indirect effects.

  • Generates 90% bias-corrected bootstrap confidence intervals for the indirect effects using 1,000 bootstrap samples.