Mediation Analysis in AMOS

[Draft]

Purpose: To name 2 parameters and create an indirect effect out of them.

File to use: Causal Model Imputed or Latent

1. Save a new model 5 Path Mediation.
2. Make sure the model fit is good enough. Pass the global test and R square.
3. Go to Statwiki — get the AMOS AxB estimand — save it in the correct folder
• for instructions, go to …….
4. In AMOS, select estimands (lower left of AMOS) — a folder will open — Locate the estimand -- Open
5. Refer to the hypothesized model for the mediation required.
6. Name the two paths that form the indirect effect.
• Double click the path — Parameter — Regression weight — name A
• Double click the other path — Parameter — Regression weight — name B
7. Analysis properties — Bootstrap — Perform bootstrap — 2000 samples — Bias corrected — 90% confidence level — Close.
8. Save — Run
9. Outputs — Estimates — Scalars — User-defined estimands — the standardized indirect will be shown (AxB)
10. Go down to Estimates/Bootstrap — Bias corrected — gives the P-value of the indirect effect.
11. List and interpret the results
• List the estimate (standardized indirect effect or AxB)
• List the p-value (must be less than 0.10 at least or 0.50)
• Is the hypothesis supported?
12. Repeat the process above to test other paths
• Get rid of the previous paths
• Name new paths