A Study on Factor Analytical Methods and Procedures for PLS-SEM (Partial Least Squares Structural Equation Modeling)

Abstract

Purpose -This study provides appropriate procedures for EFA to help researchers conduct empirical studies by using PLS-SEM. Research design, data, and methodology -This study addresses the absolute and relative sample size criteria, sampling adequacy, factor extraction models, factor rotation methods, the criterion for the number of factors to retain, interpretation of results, and reporting information. Results -The factor analysis procedure for PLS-SEM consists of the following five stages. First, it is important to look at whether both the Bartlett test of sphericity and the KMO MSA meet the qualitative criteria. Second, PAF is a better choice of methodology. Third, an oblique technique is a suitable method for PLS-SEM. Fourth, a combined approach is strongly recommended to factor retention. PA should be used at the onset. Next, it is recommended using the K1 criterion. In addition, it is necessary to extract factors that increase the total variance explanatory power through the PVA-FS. Finally, it is appropriate to select an item with a factor loading into 0.5 or higher and a communality of 0.5. Conclusions -It is expected that the accurate factor analysis processed for PLS-SEM as previously presented will help us extract more precise factors of the structural model.

Internal Motivations, External Contexts, and Sustainable Consumption Behavior in China—Based on the TPB-ABC Integration Model

“…As shown in Table 3, the Cronbach's alpha values for the measurement model range from 0.702 to 0.886, and the composite reliability values range from 0.835 to 0.930, all of which are above 0.7, which indicates that the internal consistency reliability of the scale indicators of the measurement model is acceptable. The eigenvalues (Eig) of the correlation matrix are another criterion indicating the appropriateness of the measured variable in reflecting the corresponding latent variable [95,101]. According to Sanchez [95], if the first eigenvalue in the correlation matrix is higher than 1 and the second eigenvalue is lower than 1, each group of indicators is in a unidimensional space.…”

The Malay version of the attitudes and beliefs about cardiovascular disease (ABCD-M) risk questionnaire: a translation, reliability and validation study

“…Most of the items had good FLs (> 0.50) and low complexity, except for item 15 under the domain ‘perceived risk of heart attack/stroke’, which had low FL (0.26) and communality (0.122) and high complexity (2.06). In addition, almost all items had good communality values ranging from 0.32 to 0.94 [ 17 , 40 ].…”

“…It ought to be relatively easy to understand for the general population in Malaysia regardless of sociodemographic differences. Furthermore, the use of the EFA and CFA provides more robust evidence to support the validity of the factor structure of a measure [ 40 ]. There are limited studies that use the CFA even though the method is proven superior to the EFA and other simple reliability analyses in several respects [ 31 , 49 ].…”

“…If the items measured the same single construct and have the same FLs and there were no error covariances, Raykov’s rho and Cronbach’s alpha would be the same, or the discrepancy between the values would be very close [ 50 ]. The FLs of the items were good as the values were more than 0.5 [ 17 , 40 ]. However, item 15 under the domain ‘perceived risk of heart attack/stroke’ had low FL (< 0.30) and communality (< 0.25) and high complexity.…”

Exploring the Factors Associated with Climate-Related Issues in a Special Economic Development Zone: Application of a DPSIR Framework

“…There are several limitations to this study, the recording of the amount of historical data being the preliminary limitation. With regards to factor analysis, a larger number of samples contribute to more robust results [52]. Comprehensively, as the geographical scope of this study was restricted to district level boundaries, the data pertaining to the collection of long and continuous historical time-series was assiduously challenging in nature.…”