Partial Least Square (PLS) Method of Addressing Multicollinearity Problems in Multiple Linear Regressions (Case Studies: Cost of electricity bills and factors affecting it)

University or college is a challenging reality leading to a sometimes elusive career path. By consulting social media and review websites, students have more alternatives to consider in their choice determination. This study develops a multifaceted model to recognize the influence of service quality and e-word of mouth on customer satisfaction and the impact of customer satisfaction on word of mouth. Data gathered from a sample of 150 university students are analyzed by SPSS and PLS-SEM. The findings indicate that service quality dimensions and e-WOM have positive impacts on customer satisfaction. Furthermore, this study reinforces that customer satisfaction has a positive influence on customers’ WOM intentions. This research recommends that university management should consider the importance of service quality factors and social media channels to meet and exceed students’ expectations in order to bolster the quality of services and boost customer satisfaction.

show abstract

“…As an empirical rule, the more this factor exceeds 5, the more the co-linear rate also increases (max. 5) [64][65][66][67].…”

mentioning

confidence: 99%

Influence of Online Reviews on Student Satisfaction Seen through a Service Quality Model

Torabi

Bélanger

2021

JTAER

View full text Add to dashboard Cite

show abstract

“…There are 2 requirements regarding the sample size. First, the ratio of the sample size to the number of parameters should be greater than 5:1 [ 57 ]; second, the sample size should be greater than 10 times the largest number of either the formative items used to measure a single construct or the largest number of paths the latent variable has in the model [ 45 , 47 ]. In this study, the number of parameters is 7, the number of formative items is 3, and the number of paths the latent variable has is 10.…”

Section: Resultsmentioning

confidence: 99%

“…The research model was tested by partial least squares structural equation modelling (PLS-SEM) using the software program SmartPLS (version 3.0, SmartPLS GmbH) [ 39 , 45 , 46 ]. The PLS-SEM is commonly used to model the dynamic relationships between antecedent variables and dependent variables, thereby addressing the limitation of the multiple regression model with a relatively fixed relationship between variables and multicollinearity issues [ 47 ]. Moreover, the average number of latent variables in PLS-SEM is 7.94, which is much higher than 4.70 in covariance-based SEM [ 46 ].…”

Section: Methodsmentioning

confidence: 99%

Measuring Success of Patients’ Continuous Use of Mobile Health Services for Self-management of Chronic Conditions: Model Development and Validation

Song¹,

Deng²,

Cui³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

Background Mobile health services are gradually being introduced to support patients’ self-management of chronic conditions. The success of these services is contingent upon patients’ continuous use of them. Objective This study aims to develop a model to measure the success of patients’ continuous use of mobile health services for the self-management of chronic conditions. Methods The proposed model was derived from the information systems continuance model and the information systems success model. This model contains 7 theoretical constructs: information quality, system quality, service quality, perceived usefulness, user satisfaction, perceived health status, and continuous use intention. A web-based questionnaire survey instrument was developed to test the model. The survey was conducted to collect data from 129 patients who used a mobile health app for hypertension management from 2017 to 2019. The questionnaire items were derived from validated instruments and were measured using a 5-point Likert scale. The partial least squares modelling method was used to test the theoretical model. Results The model accounted for 58.5% of the variance in perceived usefulness (R2=0.585), 52.3% of the variance in user satisfaction (R2=0.523), and 41.4% of the variance in patients’ intention to make continuous use of mobile health services (R2=0.414). The continuous use intention was significantly influenced by their perceived health status (β=.195, P=.03), perceived usefulness (β=.307, P=.004), and user satisfaction (β=.254, P=.04) with the mobile health service. Information quality (β=.235, P=.005), system quality (β=.192, P=.02), and service quality (β=.494, P<.001) had a significantly positive influence on perceived usefulness but not on user satisfaction. Perceived usefulness had a significantly positive influence on user satisfaction (β=.664, P<.001). In a result opposite to the original hypothesis, perceived health status did not negatively influence patients’ intention to continue using the mobile health service but showed a significantly positive correlation. Conclusions This study developed a theoretical model to predict and explain patients’ continuous use of mobile health services for self-management of chronic conditions and empirically tested the model. Perceived usefulness, user satisfaction, and health status contributed to patients’ intention to make continuous use of mobile health services for self-managing their chronic conditions.

show abstract

“…However, multicollinearity has been shown to be less problematic in large samples compared to smaller ones ( James et al, 2013 ). In contrast, the PLS methods are largely robust to multicollinearity ( Palermo et al, 2009 ; Wondola et al, 2020 ). Finally, it is important to note that the loadings of particular brain regions and psychopathology factors on the latent variables yielded by CCA/PLSC/PLSR analysis may vary slightly across different algorithms and software platforms.…”

Section: Discussionmentioning

confidence: 99%

Multivariate analytical approaches for investigating brain-behavior relationships

Durham,

Ghanem,

Stier

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

BackgroundMany studies of brain-behavior relationships rely on univariate approaches where each variable of interest is tested independently, which does not allow for the simultaneous investigation of multiple correlated variables. Alternatively, multivariate approaches allow for examining relationships between psychopathology and neural substrates simultaneously. There are multiple multivariate methods to choose from that each have assumptions which can affect the results; however, many studies employ one method without a clear justification for its selection. Additionally, there are few studies illustrating how differences between methods manifest in examining brain-behavior relationships. The purpose of this study was to exemplify how the choice of multivariate approach can change brain-behavior interpretations.MethodWe used data from 9,027 9- to 10-year-old children from the Adolescent Brain Cognitive DevelopmentSM Study (ABCD Study®) to examine brain-behavior relationships with three commonly used multivariate approaches: canonical correlation analysis (CCA), partial least squares correlation (PLSC), and partial least squares regression (PLSR). We examined the associations between psychopathology dimensions including general psychopathology, attention-deficit/hyperactivity symptoms, conduct problems, and internalizing symptoms with regional brain volumes.ResultsThe results of CCA, PLSC, and PLSR showed both consistencies and differences in the relationship between psychopathology symptoms and brain structure. The leading significant component yielded by each method demonstrated similar patterns of associations between regional brain volumes and psychopathology symptoms. However, the additional significant components yielded by each method demonstrated differential brain-behavior patterns that were not consistent across methods.ConclusionHere we show that CCA, PLSC, and PLSR yield slightly different interpretations regarding the relationship between child psychopathology and brain volume. In demonstrating the divergence between these approaches, we exemplify the importance of carefully considering the method’s underlying assumptions when choosing a multivariate approach to delineate brain-behavior relationships.

show abstract

Partial Least Square (PLS) Method of Addressing Multicollinearity Problems in Multiple Linear Regressions (Case Studies: Cost of electricity bills and factors affecting it)

Cited by 13 publications

References 0 publications

Influence of Online Reviews on Student Satisfaction Seen through a Service Quality Model

Influence of Online Reviews on Student Satisfaction Seen through a Service Quality Model

Measuring Success of Patients’ Continuous Use of Mobile Health Services for Self-management of Chronic Conditions: Model Development and Validation

Multivariate analytical approaches for investigating brain-behavior relationships

Contact Info

Product

Resources

About