Examining Passenger Loyalty in Phnom Penh Public Bus System: A Structural Equation Modelling Approach

Position effects may occur in both paper–pencil tests and computerized assessments when examinees respond to the same test items located in different positions on the test. To examine position effects in large-scale assessments, previous studies often used multilevel item response models within the generalized linear mixed modeling framework. Using the equivalence of the item response theory and binary factor analysis frameworks when modeling dichotomous item responses, this study introduces a structural equation modeling (SEM) approach that is capable of estimating various types of position effects. Using real data from a large-scale reading assessment, the SEM approach is demonstrated for investigating form, passage position, and item position effects for reading items. The results from a simulation study are also presented to evaluate the accuracy of the SEM approach in detecting item position effects. The implications of using the SEM approach are discussed in the context of large-scale assessments.

Rail transportation is crucial for any strategy aiming to increase the use of public transportation at the expense of private travel. This chapter aims to contribute to the discussion by describing and comparing two different methods for analysing rail service quality, both based on user perceptions, in the context of the rail services offered by Italian operators in the north of the country. These methods are the Classification and Regression Tree Approach (CART) and the Structural Equation Modelling (SEM) approach. The CART approach suggests that factors such as cleanliness, availability of information, comfort and quality of service are most important. These results were confirmed by the SEM approach, according to which aspects regarding information, cleanliness and service have the highest positive effects on overall service quality.

For a low-income Cambodian citizen, commuting to and from work is one of the most dangerous parts of their job. In Phnom Penh, the capital city of Cambodia, low-income citizens commute by truck or long-tail remork. This sort of transportation would be dangerous on the road. Thousands of workers get to and from work every day in vans, but this massive transportation system is almost completely unregulated. Most of the drivers are independent contractors, and few receive any training. The number of traffic accidents is increasing every year, especially for low-income groups. This research is a study on the negative experiences of low-income citizen commute and their intentions toward public bus in Phnom Penh. To achieve the research and study objectives, a questionnaire survey was conducted on low-income citizens, such as factory workers. The effects were investigated using structural equation modeling based on data collected from 476 people in Phnom Penh, Cambodia, in August 2022. The model of structure develops with five latent variables: ‘negative experience in a traffic accident’, ‘Service quality’, ‘Perceived value’, ‘Involvement’, satisfaction, and behavioral intention'. For the result, the transport mode of the low-income citizen depends not only on their income but also on public transport availability, job location, and community location. The results of this research could be used to operate effectively and help policymakers develop and implement policies, along with recommendations to improve safety for commuters and their intentions to use public transport.

As Phnom Penh experiences rapid population growth and economic expansion, traffic congestion has worsened, largely due to the increasing ownership of private motorcycles. Despite the introduction of public bus services, adoption remains low as concerns over service quality, limited coverage, and inadequate infrastructure deter motorcycle users from making the shift. This study investigates the behavioral intentions, preferences, and concerns of motorcycle users, specifically targeting university students, to understand how public bus services can be improved to encourage adoption. Data were collected in July 2024 from 457 university students who regularly use motorcycles, using a structured questionnaire across four Phnom Penh universities. The analysis, incorporating descriptive statistics and Structural Equation Modeling (SEM), revealed that while certain service aspects, like comfort, are appreciated, barriers such as limited punctuality, frequency, and accessibility hinder wider adoption. The findings suggest that improving service quality alone may not suffice; sequential enhancements in satisfaction, social influence, and involvement are crucial for encouraging public bus use. Recommendations include implementing bus priority lanes, expanding routes to underserved areas like Sen Sok, and reducing congestion to increase accessibility and reliability. This study provides strategic insights for sustainable transportation planning to reduce motorcycle dependence and promote public transit adoption in Phnom Penh.

<p style="text-align: justify;">This study used the structural equation modeling (SEM) approach to test a model that hypothesized the influence of self-efficacy, self-control, emotion, and engagement on student academic performance. The structural equation modeling model was developed to link all the study variables with a literature review to describe the interrelationship. Data collected were from 413 college students in their second year. The results show that self-efficacy, self-control, emotion, and engagement predict student academic performance. And through emotion and student engagement, both self-efficacy and self-control predict student academic performance indirectly. Practically the measures used in this study give more information about the learning environment in higher education settings than those usually come from traditional practices faculty received in the classroom, such as student rating forms and feedback. The main findings of this study have some implications for higher education, theory development, measurement, and future research.</p>

Nursing students’ nomophobia, social media use, attention, motivation, and academic performance: A structural equation modeling approach

Gross manual dexterity is an important part of human factors and ergonomics. The purpose of the current study was to investigate factors affecting gross manual dexterity. Gender, palm length, grip strength, hand skin temperature, room temperature, and room humidity were analyzed simultaneously to predict gross manual dexterity by utilizing Structural Equation Modeling (SEM) approach. SEM showed that hand skin temperature was the most important factor for predicting gross manual dexterity, followed by several other factors such as grip strength, gender, and room temperature. In addition, room humidity, age, and hand size were also had significant indirect effects on gross manual dexterity. The SEM derived in this study could be a very valuable theoretical foundation which could be very beneficial for human factors engineer, physical therapist, and even medical doctors.

Factors affecting response actions of the 2020 Taal Volcano eruption among Filipinos in Luzon, Philippines: A structural equation modeling approach

Aim/Purpose: This study examined how service fairness and SERVQUAL dimensions influenced customer satisfaction and loyalty in mobile financial applications (MFAs) in Phnom Penh, Cambodia. As digital transformation reshapes financial services, understanding these factors is crucial for improving user experiences and fostering long-term engagement. Introduction/Background: Mobile financial applications (MFAs) have become an essential part of Cambodia’s urban financial ecosystem by providing accessible and cost-effective financial solutions. Despite their increasing usage, limited research exists on the factors influencing customer satisfaction and loyalty in this sector. This study aimed to bridge this gap by examining how service fairness dimensions (distributive, procedural, interpersonal, and informational) and SERVQUAL dimensions (reliability, responsiveness, assurance, and empathy) impacted customer satisfaction and loyalty. Methodology: A quantitative research methodology was employed to explore the relationships among service fairness, SERVQUAL factors, customer satisfaction, and loyalty. The study targeted individuals aged 18 and above who actively use MFAs in Phnom Penh. Due to the absence of precise population data, stratified purposive sampling was used to ensure diverse representation across Phnom Penh’s districts. Using Cochran’s formula with a 95% confidence level and a 5% margin of error, the study aimed for a sample size of 400 respondents, but 560 surveys were distributed to enhance reliability, yielding 470 valid responses. Data collection took place between May and July 2024 through online surveys and self-administered questionnaires distributed across various digital platforms. The survey instrument was structured into four key sections: demographic information, MFA usage experience, behavioral factors, and service fairness/SERVQUAL dimensions, which were measured on a five-point Likert scale. Survey items were adapted from prior studies to ensure measurement reliability and validity. The questionnaire was pretested with 30 respondents, and refinements were made to improve clarity and relevance. Advanced statistical techniques were used to analyze the data. Descriptive statistics provided an overview of respondent demographics and usage behavior. Cronbach’s Alpha was employed to assess reliability, while Confirmatory Factor Analysis (CFA) validated the construct dimensions. Structural Equation Modeling (SEM) was utilized to test the relationships among service fairness, service quality, customer satisfaction, and loyalty, with results presented through detailed statistical models and tables. Findings: The study revealed that both service fairness and SERVQUAL dimensions significantly influenced customer satisfaction, which, in turn, drives customer loyalty. Among service fairness dimensions, distributive and procedural fairness had the strongest effects on satisfaction, highlighting the importance of transparent processes and fair service outcomes. Customers responded positively to equitable resource allocation and well-structured procedural guidelines. Regarding SERVQUAL dimensions, responsiveness and assurance emerged as the most influential factors shaping customer satisfaction. Customers highly valued prompt responses to inquiries and the expertise and reliability of service providers. While empathy contributed to satisfaction, its impact was comparatively less pronounced. Customer satisfaction was found to mediate the relationships between service fairness, service quality, and loyalty. This underscored the necessity of fostering positive user experiences to enhance long-term customer retention and loyalty. The findings suggest that MFA providers should prioritize procedural fairness and responsiveness to optimize customer satisfaction and long-term engagement. Contribution/Impact on Society: This study provides empirical evidence of the role of service fairness and SERVQUAL factors in shaping customer satisfaction and loyalty in the Cambodian MFA market. While previous research has examined these factors in other industries, this study uniquely focused on MFAs in a developing Southeast Asian context. The findings emphasize the importance of fair service design and high-quality service delivery in building customer trust and loyalty. By implementing transparent service processes and prioritizing customer support quality, MFA providers can foster financial inclusion and promote sustainable business growth in emerging markets. Recommendations: For MFA providers, the study recommends emphasizing transparency, equitable service outcomes, and efficient customer support to enhance satisfaction and trust. Specifically, providers should: Improve distributive and procedural fairness by implementing clear, transparent, and fair resource allocation policies. Enhance responsiveness by ensuring customer inquiries are addressed promptly and effectively. Strengthen assurance through professional training programs that enhance staff expertise and reliability. Invest in customer service training to improve staff empathy and engagement with users. For researchers, further exploration into additional variables such as trust, security, and digital literacy could offer a more comprehensive understanding of MFA user behavior. Research Limitation: This study had several limitations. Its cross-sectional research design captured data at a single point in time, limiting the ability to infer causal relationships. Additionally, the study focused exclusively on Phnom Penh, restricting the generalizability of findings to other regions or countries. The reliance on self-reported data may have introduced potential bias, including social desirability bias. Future studies should adopt longitudinal designs and include a broader geographic scope to enhance research validity Future Research: Future studies should expand on this research by incorporating additional factors such as perceived security, trust, and digital literacy to provide deeper insights into customer satisfaction and loyalty in MFAs. Comparative studies across different regions or countries could reveal cultural differences in how service fairness and quality affect customer perceptions. Additionally, longitudinal studies tracking changes in satisfaction and loyalty over time would provide a dynamic perspective on user behavior and evolving service expectations.

Limitations record on a variable which have continuous variable changes make the 'time' attached to the data is discrete. That underlies development of continuous time model. Compared to discrete time model, the continuous time model has advantages that can make prediction at different lag. In addition, it still can perform continuous time model parameter estimation, although the objects observations do not always have the same time interval (irregular time). Thus, the purpose of this study is to examine the consistency of continuous time model coefficient parameter with structural equation model (SEM) approach in irregular time data. The method used is the Exact Discrete Model (EDM) with SEM approach. EDM is a model that connects the parameter to value which is underlying parameter of the continuous time model with non-linear relationships. The result analysis of the research indicated that the coefficients of continuous time model parameter are still consistent until 20% of irregular time with 5% consistency limits.

This paper aims to identify the major significant dimensions that contribute to the overall quality of life (QOL) of wage workers in Egypt. As the QOL is a complex, multidimensional, and interdisciplinary concept, forty-seven indicators under five domains were chosen to investigate the QOL determinants of wage workers in Egypt, namely job characteristics, job satisfaction, ICT access, gender equality and women empowerment, and neighborhood services and utilities. Using data from the 2018 wave of the Egypt Labor Market Panel Survey, the paper employed structural equation modelling (SEM) approach to investigate the impact of proposed dimensions on the overall QOL. In addition, multi-group SEM analysis was implemented to measure how people differ in the way they assess their QOL on the basis of various moderating variables such as the geographical region of residence, age group, and years of schooling. The findings showed the significant impact of the chosen dimensions on the overall QOL. Moreover, the multi-group models showed a significant variation among compared groups, in which the weights of dimensions vary due to the differences in socio-cultural characteristics and the surrounding environment, confirming the complexity of such a concept. As people usually differ in the way they assess their QOL, which is affected by their characteristics and priorities.

This paper concerns the divisibility of comprehension subskills measured in L2 listening and reading tests. Motivated by the administration of the new Web-based English as a Second Language Placement Exam (WB-ESLPE) at UCLA, this study addresses the following research questions: first, to what extent do the WB-ESLPE listening and reading items measure different comprehension subskills? Second, to what extent can L2 listening and reading be considered similar or different, with regard to the divisibility of comprehension subskills? Employing a structural equation modeling (SEM) approach, the factor structures of 110 test takers' scores on the WB-ESLPE listening and reading items were examined with regard to three types of subskills, that is, `understanding main/topical ideas', `understanding supporting/specific details', and `making inferences'. The results of the analyses indicated that the WB-ESLPE listening and reading items measure two or three kinds of subskills, and that while L2 listening and reading might share a common comprehension process, they may be distinct in the decoding processes involved due to the difference in mode of presentation. It is suggested that this divisibility of subskills in L2 comprehension tests might depend on the test takers' L2 proficiency as well as on the task characteristics of the test administered to them.

The present study examined the factor structure of the University of Tehran English Proficiency Test (UTEPT) that aims to examine test takers’ knowledge of grammar, vocabulary, and reading comprehension. A Structural Equation Modelling (SEM) approach was used to analyse the responses of participants (N= 850) to a 2010 version of the test. A higher-order model was postulated to test if the underlying factor structure, obtained in a data-driven manner, corresponds with the proposed structure of the test. The results revealed an appropriate model fit with the data, pointing to the fact that the three sections of UTEPT, i.e., structure, vocabulary, and reading, and their sub-components, except for the restatement section of reading, are good indicators of written language proficiency as assessed by the UTEPT. It was also found that the three sections assess distinctive constructs. The findings suggest that UTEPT is a valid measure of the written language proficiency of Ph.D. applicants to University of Tehran.

Purpose This study used extended Unified Theory of Acceptance and Use of Technology (UTAUT) model to examine the effect of personal expectancy (PE), efforts expectancy (EE), social influence (SI), facilitating conditions (FC), hedonic motivation (HM), price value (PV) and habit (H) on behavioural intention (BI) to use Chat Generative Pre-Trained Transformer (ChatGPT) in higher education for an Indian context. The study also examined moderating effects of students’ self-innovativeness (SIN) and integrity (INT) on the relationship between BI and use behaviour (UB) for ChatGPT. Design/methodology/approach A sample of 311 students has been selected from Northern states of India by applying stratified proportionate random sampling method and four disciplines – engineering, business administration, science and fine arts were used as different strata in the sample selection process. Partial least squares structural equation modelling (PLS-SEM) approach has been used in data analysis to assess proposed theoretical model. Findings The study found PE, FC, PV and H significantly account for students’ BI and actual use of ChatGPT, whereas EE, SI and HM showed a negligible impact on BI. The BI was also found non-significant in predicting the usage behaviour for ChatGPT. The moderation effects of SIN and INT of students were also found non-significant on the relationship between BI and UB. Research limitations/implications A limited sample size of study and its focus on Northern states of India constrain the generalizability of findings to the other parts of world. Originality/value The study helps to understand the nuances associated with advanced artificial intelligence (AI)-driven tool such as ChatGPT in higher education for the application of best-practices. Therefore, this study aims to bridge this gap by examining determinants of ChatGPT usage with extended version of UTAUT model in Indian context by using additional constructs such as SIN and INT.

Modeling passengers’ loyalty to public transit in a two-dimensional framework: A case study in Xiamen, China