Electronic Journal of Applied Statistical Analysis

Applied Statistical Analysis using PLS Path Modeling

Jun-Hwa (Jacky) Cheah^(a), Mumtaz Ali Memon^(b), Man-Lai Cheung^(c), Hiram Ting^(d)

^(a)University of East Anglia, United Kingdom
^(b)NUST Business School, National University of Sciences and Technology, Islamabad, Pakistan
^(c)University of Newcastle, Australia
^(d)UCSI University and Sarawak Research Society, Malaysia

The main theme of this special issue is “Applied Statistical Analysis using PLS Path Modelling” with the contribution of eight papers. Most of the contributions are inspired by the International Symposium on Applied Structural Equation Modelling and Methodological Matter 2019 (SASEM 2019) which took place in Malaysia. During the symposium, scholars from social sciences had the opportunity to share their idea on the Partial Least Squares Path Modeling (PLSPM) method, which addressing to methodological issues and real applications in various social science fields, such as business, agricultural science, engineering, and medicine. The application of the method was beneficial to any field because it can deal with small sample sizes and non-normal distribution (Hair et al., 2022). In addition, if the aim of the research is to (i) predict key target constructs and identify key driver constructs, and (ii) explore (and extend) an existing structural theory, the reasons would fit PLSPM like “hand in glove” (Chin et al., 2020; Hair et al., 2022). Therefore, we strongly believe the method will continue to grow exponentially, with more powerful graphical user programs that are user-friendly (i.e., SmartPLS4, ADANCO, WarpPLS, etc.), new development of PLSPM techniques (i.e., PLSpredict, cross-validated predictive ability test, conditional mediation model, etc.), and PLS guideline research materials (Becker et al., 2023; Cheah et al., 2021; 2023; Guenther et al., 2023; Hair et al., 2022; Sarstedt and Cheah, 2019).

Download Full Editorial