Regression Analysis with Latent Variables by Partial Least Squares and Four Other Composite Scores: Consistency, Bias and Correction

Yuan, Ke‐Hai; Yue, Wen; Tang, Jiashan

doi:10.1080/10705511.2019.1647107

Cited by 33 publications

(30 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This practice is problematic as it ignores the attenuating effect of measurement error. Numerous studies have shown that failure to correct for measurement error produces a combination of under- and over-estimation in the estimates of the entire nomological network (e.g., Cole & Preacher, 2014; Hair, Hult, Ringle, Sarstedt, & Thiele, 2017; Yuan et al, 2020). In contrast, SEM methods permit the elimination of measurement error in the analyses.…”

Section: Process Versus Pls-semmentioning

confidence: 99%

Beyond a tandem analysis of SEM and PROCESS: Use of PLS-SEM for mediation analyses!

Sarstedt

Hair

Nitzl

et al. 2020

International Journal of Market Research

451

258

View full text Add to dashboard Cite

Mediation and conditional process analyses have become popular approaches for examining the mechanisms by which effects operate and the factors that influence them. To estimate mediation models, researchers often augment their structural equation modeling (SEM) analyses with additional regression analyses using the PROCESS macro. This duality is surprising considering that research has long acknowledged the limitations of regression analyses when estimating models with latent variables. In this article, we argue that much of the confusion regarding SEM’s efficacy for mediation analyses results from a singular focus on factor-based methods, and there is no need for a tandem use of SEM and PROCESS. Specifically, we highlight that composite-based SEM methods overcome the limitations of both regression and factor-based SEM analyses when estimating even highly complex mediation models. We further conclude that composite-based SEM methods such as partial least squares (PLS-SEM) are the preferred and superior approach when estimating mediation and conditional process models, and that the PROCESS approach is not needed when mediation is examined with PLS-SEM.

show abstract

Section: Process Versus Pls-semmentioning

confidence: 99%

Beyond a tandem analysis of SEM and PROCESS: Use of PLS-SEM for mediation analyses!

Sarstedt

Hair

Nitzl

et al. 2020

International Journal of Market Research

451

258

View full text Add to dashboard Cite

show abstract

“…This practice is problematic as it ignores the attenuating effect of measurement error. Numerous studies have shown that the failure to correct for measurement error produces a combination of under and over-estimation in the relationships among constructs in a larger nomological network (Cole and Preacher, 2014;Hair et al, 2017;Yuan et al, 2020). By contrast, SEM methods permit the elimination of measurement error in the analyses (Cole and Preacher, 2014).…”

Section: Combining Fuzzy-set Qualitative Comparative Analysis With Partial Least Squares Structural Equation Modelingmentioning

confidence: 99%

“…This practice is problematic as it ignores the effect of measurement error inherent in the indicators (Sarstedt et al, 2016). By contrast, the individual weighting of the indicators in a PLS-SEM analysis accounts for measurement error, thereby increasing the reliability and validity of the model estimates (Yuan et al, 2020). For example, Hair et al (2017) have shown IJCHM 33,5 that sum scores can produce substantial parameter biases and often lag behind PLS-SEM in terms of statistical power.…”

Section: Introductionmentioning

confidence: 99%

The combined use of symmetric and asymmetric approaches: partial least squares-structural equation modeling and fuzzy-set qualitative comparative analysis

Rasoolimanesh

Ringle

Sarstedt

et al. 2021

IJCHM

242

148

View full text Add to dashboard Cite

Purpose This study aims to propose guidelines for the joint use of partial least squares structural equation modeling (PLS-SEM) and fuzzy-set qualitative comparative analysis (fsQCA) to combine symmetric and asymmetric perspectives in model evaluation, in the hospitality and tourism field. Design/methodology/approach This study discusses PLS-SEM as a symmetric approach and fsQCA as an asymmetric approach to analyze structural and configurational models. It presents guidelines to conduct an fsQCA based on latent construct scores drawn from PLS-SEM, to assess how configurations of exogenous constructs produce a specific outcome in an endogenous construct. Findings This research highlights the advantages of combining PLS-SEM and fsQCA to analyze the causal effects of antecedents (i.e., exogenous constructs) on outcomes (i.e., endogenous constructs). The construct scores extracted from the PLS-SEM analysis of a nomological network of constructs provide accurate input for performing fsQCA to identify the sufficient configurations required to predict the outcome(s). Complementing the assessment of the model’s explanatory and predictive power, the fsQCA generates more fine-grained insights into variable relationships, thereby offering the means to reach better managerial conclusions. Originality/value The application of PLS-SEM and fsQCA as separate prediction-oriented methods has increased notably in recent years. However, in the absence of clear guidelines, studies applied the methods inconsistently, giving researchers little direction on how to best apply PLS-SEM and fsQCA in tandem. To address this concern, this study provides guidelines for the joint use of PLS-SEM and fsQCA.

show abstract

“…Scholars considered it suitable for the studies examining causal associations with hypothesis testing (Arman et al, 2020;Mansoor and Noor, 2019). Thus, to test the hypothesized paths and check for the results of the direct and mediation paths, the authors of the current study applied structural equation modelling through SMART PLS 3 (Yuan et al, 2020). Serval recent studies applied this software and data analysis technique to assess the theoretical foundations of the constructs (Noor et al, 2021;Arman et al, 2020).…”

Section: Control Variablesmentioning

confidence: 99%

Perceived effectiveness of e-governance as an underlying mechanism between good governance and public trust: a case of Indonesia

Hartanto

Dalle

Akrim

et al. 2021

DPRG

View full text Add to dashboard Cite

Purpose This study aims to investigate the association of perceived accountability, perceived responsiveness and perceived transparency, and public trust in local government. Additionally, mediation of the perceived effectiveness of e-governance was also tested between these relationships. Design/methodology/approach Using a quantitative cross-sectional field survey, primary data was collected at local administration levels from two cities in Indonesia. The final data set of 355 respondents was then analyzed using SmartPls3 and the measurement and structural models were tested. Findings Positive results were obtained for all the hypothesized links (direct and indirect relationships). The study’s findings revealed useful insights for policymakers and researchers regarding the public’s perception of good governance and their expectations from the government, which further lead toward trust in local governments. Practical implications The study concluded that good governance practices develop and enhance the public’s trust in the government, thus provided key policy directions. Originality/value This study contributes to the body of knowledge related to good governance elements and their impact on public trust in the local government via the underlying mechanism of perceived e-governance effectiveness in developing countries in general and particularly the Indonesian context. Moreover, it is a unique study in the good governance domain while considering three good governance elements into a single theoretical framework. Previous studies have explored these elements individually with public trust, so this combined framework advances the body of knowledge. This research’s findings also contributed toward validating good governance theory with e-governance effectiveness and public trust integration in a single comprehensive framework. This research also helped answer the questions arising from past literature about declining public trust trends in local governments.

show abstract

Regression Analysis with Latent Variables by Partial Least Squares and Four Other Composite Scores: Consistency, Bias and Correction

Cited by 33 publications

References 31 publications

Beyond a tandem analysis of SEM and PROCESS: Use of PLS-SEM for mediation analyses!

Beyond a tandem analysis of SEM and PROCESS: Use of PLS-SEM for mediation analyses!

The combined use of symmetric and asymmetric approaches: partial least squares-structural equation modeling and fuzzy-set qualitative comparative analysis

Perceived effectiveness of e-governance as an underlying mechanism between good governance and public trust: a case of Indonesia

Contact Info

Product

Resources

About