[Knowledge Sharing 28] 知識分享 

Top 22 common errors and 8 new guidelines for SEM 

2023 New guideline (Issue) 7：blindfolding-based Q square metric

The blindfolding-based Q square metric should be used to assess a model’s “predictive relevance”

==》

(new guideline) The blindfolding-based Q square is not a reliable indicator of explanatory or predictive power. Explanatory power assessment should rely on the R2, while PLSpredict or CVPAT should be used for predictive power assessment.

Reference

Shmueli, G., Ray, S., Velasquez Estrada, J. M., & Chatla, S. B. (2016). The elephant in the room: Evaluating the predictive performance of PLS models. Journal of Business Research, 69(10), 4552–4564. https://doi.org/10.1016/j.jbusres.2016. 03.049

Shmueli, G., Sarstedt, M., Hair, J. F., Cheah, J., Ting, H., Vaithilingam, S., & Ringle, C. M. (2019). Predictive model assessment in PLS-SEM: Guidelines for using PLSpredict. European Journal of Marketing, 53(11), 2322–2347. https:// doi.org/10.1108/EJM-02-2019-0189

Sarstedt, M., Hair Jr., J. F. & Ringle, C. M. (2023) “PLS-SEM: indeed a silver bullet” – retrospective observations and recent advances, Journal of Marketing Theory and Practice, 31:3, 261-275, DOI: 10.1080/10696679.2022.2056488

Wen-Lung Shiau, Ye Yuan, Xiaodie Pu, Soumya Ray, and Charlie C. Chen (2020), "Understanding fintech continuance: perspectives from self-efficacy and ECT-IS theories", Industrial Management & Data Systems, Vol. 120 No. 9, pp. 1659-1689 (SCI, Q2,2019 IF= 3.329，5-year Impact Factor : 4.379) ESI 1% highly cited article