{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Mediation Example (with bootstrap) and Moderation

# Mediation Example (with bootstrap) and Moderation - How to...

This preview shows pages 1–4. Sign up to view the full content.

How to examine a mediator relationship – An example from Project EAT (A potential moderator effect of family communication will be looked at on the last two pages) Original variables Simple Statistics Variable N Mean Std Dev Sum Minimum Maximum FAMCOMM 2834 15.15737 3.29778 42956 4.00000 20.00000 TEASEWT 2834 1.59739 1.04499 4527 1.00000 5.00000 SLFESTEM 2834 18.23536 3.53311 51679 6.00000 24.00000 UWCB_YR 2834 0.90261 1.39272 2558 0 9.00000 Pearson Correlation Coefficients, N = 2834 Prob > |r| under H0: Rho=0 FAMCOMM TEASEWT SLFESTEM UWCB_YR FAMCOMM 1.00000 -0.15277 0.32131 -0.21047 <.0001 <.0001 <.0001 TEASEWT -0.15277 1.00000 -0.27807 0.18309 <.0001 <.0001 <.0001 SLFESTEM 0.32131 -0.27807 1.00000 -0.39734 <.0001 <.0001 <.0001 UWCB_YR -0.21047 0.18309 -0.39734 1.00000 <.0001 <.0001 <.0001 Using Proc Standard in SAS create Standardized variables Simple Statistics Variable N Mean Std Dev Sum Minimum Maximum xfamcomm 2834 0 1.00000 0 -3.38330 1.46845 xteasewt 2834 0 1.00000 0 -0.57167 3.25613 xslfestem 2834 0 1.00000 0 -3.46305 1.63160 xuwcb_yr 2834 0 1.00000 0 -0.64809 5.81406 Pearson Correlation Coefficients, N = 2834 Prob > |r| under H0: Rho=0 xfamcomm xteasewt xslfestem xuwcb_yr xfamcomm 1.00000 -0.15277 0.32131 -0.21047 <.0001 <.0001 <.0001 xteasewt -0.15277 1.00000 -0.27807 0.18309 <.0001 <.0001 <.0001 xslfestem 0.32131 -0.27807 1.00000 -0.39734 <.0001 <.0001 <.0001 xuwcb_yr -0.21047 0.18309 -0.39734 1.00000 <.0001 <.0001 <.0001 xslfestem xuwcb_yr xteasewt e1 1 e2 1 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Step 1. Test Total effect of teasing on uwcb Dependent Variable: xuwcb_yr Sum of Source DF Squares Mean Square F Value Pr > F Model 1 94.963637 94.963637 98.22 <.0001 Error 2832 2738.036363 0.966821 R-Square Coeff Var Root MSE xuwcb_yr Mean 0.033521 -1.9992E17 0.983270 -0.000000 Source DF Type III SS Mean Square F Value Pr > F xteasewt 1 94.96363655 94.96363655 98.22 <.0001 Standard Parameter Estimate Error t Value Pr > |t| Intercept -.0000000000 0.01847026 -0.00 1.0000 xteasewt 0.1830861032 0.01847352 9.91 <.0001 Notice this is the exact same as the simple correlation between xteasewt and xuwcb_yr. Step 2. Test the relationship between teasing and the mediator Dependent Variable: xslfestem Sum of Source DF Squares Mean Square F Value Pr > F Model 1 219.050183 219.050183 237.32 <.0001 Error 2832 2613.949817 0.923005 R-Square Coeff Var Root MSE xslfestem Mean 0.077321 3.93737E15 0.960731 2.44E-14 Source DF Type III SS Mean Square F Value Pr > F xteasewt 1 219.0501829 219.0501829 237.32 <.0001 Standard Parameter Estimate Error t Value Pr > |t| Intercept 0.0000000000 0.01804688 0.00 1.0000 xteasewt -.2780664054 0.01805006 -15.41 <.0001 2