当代中介分析:常见问题 五：是否以「部分中介」或「完全中介」描述结果，未依循Zhao等人 (2010) 分析中介类型？ by Shiau et al. (2026) and Zhao et al. (2010)

Source from: Shiau, W.-L., Shih, C.-H., Qureshi, I., Yuan, Y., & Teng, C.-I. (2026). Do matched and mismatched null hypothesis significance testing of mediators matter? An example of fintech continuance and guidelines for the future. Decision Support Systems, 211, 114764.

Zhao, X., Lynch, J. G., Jr., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and truths about mediation analysis. Journal of Consumer Research, 37(2), 197–206. https://doi.org/10.1086/651257

Researchers should classify and report the result for each mediation hypothesis using evidence from the indirect and direct effects. Following Zhao et al. (2010), the five classifications are complementary, competitive, indirect-only, direct-only, and no-effect. Direct-only and no-effect represent nonmediation outcomes. Researchers should report effect estimates and inferential evidence alongside each classification rather than relying solely on “partial” or “full” mediation labels. In this guideline, c denotes the direct effect after accounting for the mediator. Nonsignificance should not be interpreted as proof that an effect equals zero.

研究者应针对每项中介假设，依间接效果与直接效果的证据，报告对应的结果类型。依Zhao等人 (2010)，五种分类包括互补中介、竞争中介、仅间接效果、仅直接效果及无显著效果，其中后两类属于非中介结果。每项分类均应附上效果估计值与检定资讯，避免仅使用部分中介或完全中介，却未说明实际的效果组合。

研究者应该/不应该做的事

Reference

Shiau, W.-L., Shih, C.-H., Qureshi, I., Yuan, Y., & Teng, C.-I. (2026). Do matched and mismatched null hypothesis significance testing of mediators matter? An example of fintech continuance and guidelines for the future. Decision Support Systems, 211, 114764.

Zhao, X., Lynch, J. G., Jr., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and truths about mediation analysis. Journal of Consumer Research, 37(2), 197–206. https://doi.org/10.1086/651257

支持单位：