A Robust Bootstrap Test for Mediation Analysis

Mediation analysis is central to theory building and testing in organizational sciences. Scholars often use linear regression based on normal-theory maximum likelihood estimators test mediation. However, these are very sensitive deviations from normality assumptions, such as outliers, heavy tails, or skewness of the observed distribution. This sensitivity seriously threatens empirical about mediation mechanisms. To overcome this threat, we develop a robust method that yields reliable results even when data deviate assumptions. We demonstrate mechanics our proposed an illustrative case, while simulation studies show both superior estimating effect size more assessing its significance than existing methods. Furthermore, provide freely available software R SPSS enhance accessibility adoption by researchers.