A Monte Carlo Investigation of Partial Least Squares, With Implications for Both Structural and Measurement Models
Partial Least Squares (PLS) is a popular technique with extensive adoption within the Information Systems research community. However, the statistical performance of PLS has not been extensively studied, and recent research has questioned some of its purported advantages. The simulation study reported here analyzed the performance of PLS with regards to the recovery and estimation accuracy of both structural and measurement parameters. Somewhat surprisingly, the effects of estimation bias on the latter and their implications for the evaluation of measurement models have not been the focus of past research. Results show the existence of an important degree of bias in both sets of estimates, and the conflicting effect of increased sample size with additional indicators per composite variable.
Aguirre-Urreta, Miguel I.; Marakas, George M.; Ellis, Michael E.; and Sun, Wenying Nan, "A Monte Carlo Investigation of Partial Least Squares, With Implications for Both Structural and Measurement Models" (2008). AMCIS 2008 Proceedings. 246.