This study compares two commonly used Structural Equation Modeling (SEM) methods_Partial Least Squares SEM (PLS-SEM) and Covariance-Based SEM (CB-SEM)_to assess customer loyalty data in the telecommunications industry. The comparison was conducted using a dataset of 448 mobile service users in Melaka, where service providers have faced challenges in meeting performance standards. Findings reveal that PLS-SEM outperforms CBSEM in terms of Average Variance Extracted (AVE) and Composite Reliability (CR), with AVE values exceeding 0.68 compared to CB-SEM's 0.58, and CR values above 0.89 compared to CB-SEM's 0.84. These results highlight PLS-SEM_s superior construct reliability and validity, particularly for complex models and smaller sample sizes. This study provides valuable insights into selecting appropriate SEM techniques for customer loyalty research. Keywords: PLS-SEM, CB-SEM, customer loyalty, telecommunications, construct validity...

2 hits