The study’s findings are compromised by a critical methodological concern regarding the sample size (N=136). For the PLS-SEM analysis, this sample size provides low statistical power, risking unstable parameter estimates and unreliable significance testing. For the fsQCA, the limited number of cases threatens the generalizability of the identified configurations, as they may be artifacts of the specific sample rather than robust causal pathways.
Was an a priori power analysis conducted to justify this sample size for detecting the anticipated effect sizes?
Given the sample size, what robustness checks (e.g., bootstrap confidence intervals for R²) were performed to assess the stability of the PLS-SEM results?
How was the sensitivity of the fsQCA solutions tested against alternative frequency and consistency thresholds?