Mediation Analysis
It has been suggested that mediation analysis is to be preferred when the basic aim of a study is to identify and explore the mechanisms involved behind the relationship between predictors and outcome variables (Baron & Kenny, 1986). A mediator analysis was performed to test the third hypothesis, by using Andrew Hayes’ PROCESS plug-in for SPSS version 25 (Field, 2013). To investigate the hypothesis that the relationship between self-forgiveness and human flourishing was mediated by self-esteem, a simple mediation model was applied. We employed PROCESS Model 4 (simple mediation) to estimate regression coefficients and follow-up bootstrap analyses with 5,000 bootstrap samples to estimate 95% bias-corrected confidence intervals for specific and total indirect effects. In our study human flourishing is the dependent variable (Y) that is regressed on self-forgiveness (X), self-esteem (M) and M, is itself regressed on X. Thus, M represents the mediator variable. The indirect effect estimate of self-esteem was 0.022, with the 95% confidence interval not encompassing 0 (0.011-0.004), indicating a statistically significant mediation effect. Since all equations of the total effect, direct effect and indirect effect are showing significant results hence it indicates self-esteem partially mediates between the relationship of self-forgiveness and human flourishing.
Table 3. Showing total, direct and indirect effects of Self-Forgiveness on Human Flourishing mediated by Self-esteem
| Effect | SE | CIlow | CIup |
Total effect of self-forgiveness on human flourishing | 0.199 | 0.041 | 0.118 | 0.281 |
Direct effect of self-forgiveness on human flourishing | 0.177 | 0.042 | 0.094 | 0.263 |
Indirect effect of self-forgiveness on human flourishing mediated by positive self-esteem | 0.022 | 0.011 | 0.004 | 0.048 |