The Understanding and Application of PLS-SEM

Jing Meng is a PhD student in Economics and Business at UCL SSEES. 

Structural equation modelling (SEM) enables researchers to analyse relationships between unobservable variables (variables that are not directly observed but are instead inferred) and observable indicators measured directly. There are two types of SEM which are covariance-based SEM (CB-SEM) and partial least squares SEM(PLS-SEM). The seminar will mainly focus on PLS-SEM. Compared with the more widely-used CB-SEM, PLS-SEM works more efficiently in terms of handling small sample size, nonnormally distributed data and complex models. PLS-SEM is gaining increasing interest among researchers in economics and other social science disciplines.

The presentation will cover the understanding and application of PLS-SEM from the following aspects:

• An introduction to CB-SEM and PLS-SEM and their differences
• The situations in which the use of PLS-SEM has advantages
• Model specification of PLS-SEM
• Guidelines for data selection and examination when PLS-SEM is used
• PLS-SEM model estimation

You are welcome to join me in exploring the power of this analysis tool and seeing how to use it in research.