Mean Squared Error Of Approximation Research Articles

Measuring the quality of self-care of elderly patients with dementia in a developing country.

In developing countries like Uganda, people with dementia are cared for by non-medically trained family members with minimal support from the formal healthcare system. The quality of care in this setting is largely unknown but significantly affects the well-being of those with dementia. A tool designed to measure the quality of informal care for old frail adults with or without dementia was translated into Luganda. A committee of experts reviewed and finalized the translation, which was pilot-tested and then used to measure the quality of dementia self-care. We consecutively enrolled 105 caregivers of elderly people with dementia; the median age was 35 years (Interquartile Range 26-47 years), and 67% were females, taking care of a grandparent (44%) or a parent (34%). We used confirmatory factor analysis to assess for structural validity and computed correlation coefficients and Cronbach's alpha to assess for discriminant validity and internal reliability, respectively. The three-factor model applied to the 20 items, adequately fit the data (Comparative Fit Index = 0.88, Tucker-Lewis Index = 0.87, Root Mean Square Error of Approximation = 0.08; 90% Confidence Interval (0.06-0.09), Standardized Root Mean Square Residual = 0.089). There was good discriminant validity, and correlation coefficients between dimensions/scales and the Dementia Knowledge Assessment Scale scores were low. There was good internal reliability with all items Cronbach's alpha ranging from 0.69 to 0.89. Our findings demonstrated that this culturally adapted, shorter measurement tool is valid and reliable. The tool can be used by researchers, health workers, and agencies to assess the quality of self-care for elderly people with dementia in Uganda.

Synergizing teacher collaboration to foster active learning strategies, student engagement and achievement in physics: a unified analysis across nine countries

This investigation explores the nexus between professional teacher collaboration, active learning methodologies, teaching promoting student engagement in physics classes and physics achievement. Leveraging Trends in International Mathematics and Science Study Advanced 2015 data from 1729 physics instructors across nine countries, it probes the extent to which collaborative practices among teachers influence their teaching to enhance active learning and engagement. Analytical techniques include Spearman correlations, confirmatory factor analysis, and structural equation modeling. Results reveal a robust model, confirmed by a Comparative Fit Index of 0.989 and Tucker–Lewis Index of 0.988, suggesting a good fit with the empirical data, alongside a Root Mean Square Error of Approximation of 0.053. The analysis demonstrates that teacher collaboration (‘Collab’) significantly predicts active learning (‘Active’) with a notable effect (β = 0.344, p < 0.001), which in turn significantly enhances student engagement (‘Engage’) (β = 0.438, p < 0.001). Additionally, ‘Engage’ is also directly influenced by ‘Collab’ (β = 0.174, p < 0.001). Although the relationship between ‘Collab’ and physics achievement (‘Physics’) is weaker, it remains significant (β = 0.063, p = 0.019). These findings support the enhancement of teacher collaboration as a catalyst for active learning and student engagement, which could indirectly foster improvements in physics achievement globally.

Validation of the Learner Engagement Instrument for Continuing Professional Development.

Learner engagement is the energy learners exert to remain focused and motivated to learn. The Learner Engagement Instrument (LEI) was developed to measure learner engagement in a short continuing professional development (CPD) activity. The authors validated LEI scores using validity evidence of internal structure and relationships with other variables. Participants attended 1 of 4 CPD courses (1 in-person, 2 online livestreamed, and 1 either in-person or livestreamed) in 2018, 2020, 2021, and 2022. Confirmatory factor analysis was used to examine model fit for several alternative structural models, separately for each course. The authors also conducted a generalizability study to estimate score reliability. Associations were evaluated between LEI scores and Continuing Medical Education Teaching Effectiveness (CMETE) scores and participant demographics. Statistical methods accounted for repeated measures by participants. Four hundred fifteen unique participants attended 203 different CPD presentations and completed the LEI 11,567 times. The originally hypothesized 4-domain model of learner engagement (domains: emotional, behavioral, cognitive in-class, cognitive out-of-class) demonstrated best model fit in all 4 courses, with comparative fit index ≥ 0.99, standardized root mean square residual ≤ 0.031, and root mean square error of approximation ≤ 0.047. The reliability for overall scores and domain scores were all acceptable (50-rater G-coefficient ≥ 0.74) except for the cognitive in-class domain (50-rater G-coefficient of 0.55 to 0.66). Findings were similar for both in-person and online delivery modalities. Correlation of LEI scores with teaching effectiveness was confirmed (rho=0.58), and a small correlation was found with participant age (rho=0.19); other associations were small and not statistically significant. Using these findings, we generated a shortened 4-item instrument, the LEI Short Form. This study confirms a 4-domain model of learner engagement and provides validity evidence that supports using LEI scores to measure learner engagement in both in-person and livestreamed CPD activities.

Evaluating Imputation-Based Fit Statistics in Structural Equation Modeling With Ordinal Data: The MI2S Approach.

The multiple imputation two-stage (MI2S) approach holds promise for evaluating the model fit of structural equation models for ordinal variables with multiply imputed data. However, previous studies only examined the performance of MI2S-based residual-based test statistics. This study extends previous research by examining the performance of two alternative test statistics: the mean-adjusted test statistic (T M ) and the mean- and variance-adjusted test statistic (T MV ). Our results showed that the MI2S-based T MV generally outperformed other test statistics examined in a wide range of conditions. The MI2S-based root mean square error of approximation also exhibited good performance. This article demonstrates the MI2S approach with an empirical data set and provides Mplus and R code for its implementation.

Translation, cross-cultural adaptation, and psychometric validation of the Malay version of the Assessment of Quality of Life—6 Dimensions (Malay-AQoL-6D) instrument among Malaysians living with chronic heart failure

BackgroundThis study aimed to translate and culturally adapt the Assessment of Quality of Life (AQoL)-6D into Malay (Malay-AQoL-6D), and assesses the instrument’s acceptability, reliability, and validity among Malaysians living with chronic heart failure (HF).MethodsThe translation and cross-cultural adaptation process adhered to international guidelines. The Malay-AQoL-6D underwent content and face validity assessments via expert review, and pretesting among healthy individuals and patients with chronic conditions. Subsequent psychometric validation utilised clinico-sociodemographic data and paired AQoL-6D and EQ-5D-5L data from a health-related quality-of-life (HRQoL) survey involving Malay-speaking patients with HF, which encompassed assessments of Malay-AQoL-6D acceptability, internal consistency and test-retest reliability, as well as its construct, concurrent, convergent and divergent, and known-group validity.ResultsThe Malay-AQoL-6D was deemed acceptable among clinicians and local patients, achieving a 90.8% completion rate among 314 patients surveyed. The instrument demonstrated strong content validity (item-level content validity index [CVI]: 0.83–1.00, average CVI: 0.98), internal consistency (Cronbach’s alpha: 0.72–0.89; MacDonald’s omega: 0.82–0.90, excluding the Senses dimension), and test-retest reliability (average intraclass correlation coefficients: 0.79–0.95). Confirmatory factor analysis confirmed the instrument’s two-level, six-factor structure (Satorra-Bentler [SB]-scaled χ2(df: 164): 283.67, p-value < 0.001; root mean square error of approximation [RMSEA]: 0.051; comparative fix index [CFI]: 0.945, Tucker-Lewis index [TLI]: 0.937; standardised root mean-squared error [SRMR]: 0.058). The Malay-AQoL-6D’s concurrent validity was evident through its good agreement with EQ-5D-5L. Multiple hypothesis tests further affirmed its construct and known-group validity. The Malay-AQoL-6D’s psychometric properties remained consistent across different missing data techniques.ConclusionThe findings suggest that Malay-AQoL-6D could be a culturally acceptable, reliable, and valid HRQoL measure for quantifying HRQoL among the local HF population. Future studies are necessary to further validate the instrument against other measures and confirm the instrument’s test-retest reliability and responsiveness, which are possible with the availability of the Malay-AQoL-6D.

Structural associations between self-perception of support and knowledge of disability characteristics of autism spectrum disorder among staff in facilities providing after-school day services.

We constructed a hypothetical model of the knowledge of autism spectrum disorder (ASD) and self-perception of support of staff working in after-school day services to clarify structural relationships. A questionnaire survey was conducted at 194 facilities providing after-school day services in Fukushima Prefecture (October 2020), including a basic attributes questionnaire, the Literacy Scale of Characteristics of Autistic Spectrum Disorder (LS-ASD), and a staff questionnaire. We developed a hypothetical model of the relationship between self-perception and LS-ASD total scores of after-school service staff. To obtain latent variables for structural equation modeling (SEM) to confirm factor extraction and the interrelationships among variables, exploratory factor analysis was performed. SEM was used to examine the fit of the hypothetical model to the data and the relationships among variables. The study included 302 staff members from 58 of 194 facilities. Four factors (Factor 1, motivation; 2, self-perception of knowledge; 3, information sharing; 4, self-confidence) were extracted. The final model showed that Factor 2 had a positive direct effect (path coefficient = 0.64) and Factor 4 had a negative direct effect (path coefficient = -0.22) on LS-ASD scores. The model goodness of fit was acceptable (Goodness-of-Fit Index = 0.890; Comparative Fit Index = 0.912; Root Mean Square Error of Approximation = 0.086; Akaike's Information Criterion = 392.7). Self-perception of knowledge contributes greatly to knowledge acquisition, while excessive confidence may hinder knowledge retention.

The Parkinson's Disease Composite of Executive Functioning: A Measure for Detecting Cognitive Decline in Clinical Trials.

Executive functioning is one of the first domains to be impaired in Parkinson disease (PD), and the majority of patients with PD eventually develop dementia. Thus, developing a cognitive endpoint measure specifically assessing executive functioning is critical for PD clinical trials. The objective of this study was to develop a cognitive composite measure that is sensitive to decline in executive functioning for use in PD clinical trials. We used cross-sectional and longitudinal follow-up data from PD participants enrolled in the PD Cognitive Genetics Consortium, a multicenter setting focused on PD. All PD participants with Trail Making Test, Digit Symbol, Letter-Number Sequencing, Semantic Fluency, and Phonemic Fluency neuropsychological data collected from March 2010 to February 2020 were included. Baseline executive functioning data were used to create the Parkinson's Disease Composite of Executive Functioning (PaCEF) through confirmatory factor analysis. We examined the changes in the PaCEF over time, how well baseline PaCEF predicts time to cognitive progression, and the required sample size estimates for PD clinical trials. PaCEF results were compared with the Montreal Cognitive Assessment (MoCA), individual tests forming the PaCEF, and tests of visuospatial, language, and memory functioning. A total of 841 participants (251 no cognitive impairment [NCI], 480 mild cognitive impairment [MCI], and 110 dementia) with baseline data were included, of which the mean (SD) age was 67.1 (8.9) years and 270 were women (32%). Five hundred forty five PD participants had longitudinal neuropsychological data spanning 9 years (mean [SD] 4.5 [2.2] years) and were included in analyses examining cognitive decline. A 1-factor model of executive functioning with excellent fit (comparative fit index = 0.993, Tucker-Lewis index = 0.989, and root mean square error of approximation = 0.044) was used to calculate the PaCEF. The average annual change in PaCEF ranged from 0.246 points per year for PD-NCI participants who remained cognitively unimpaired to -0.821 points per year for PD-MCI participants who progressed to dementia. For PD-MCI, baseline PaCEF, but not baseline MoCA, significantly predicted time to dementia. Sample size estimates were 69%-73% smaller for PD-NCI trials and 16%-19% smaller for PD-MCI trials when using the PaCEF rather than MoCA as the endpoint. The PaCEF is a sensitive measure of executive functioning decline in PD and will be especially beneficial for PD clinical trials.

Guidelines for future agricultural technology development to increase productivity in the Agricultural sector

Technology development in the agricultural sector is important in the development of Thailand’s economy. The purpose of this research was to study the approach of guidelines for future agricultural technology development to increase productivity in the Agricultural sector in order to develop a structural equation model. The research applied mixed-methodology. Qualitative research by in depth interview from 9 experts and focus group with 11 successful businesspersons for approve this model. The quantitative data gather from firm, in the 500 of agricultural sector by using questionnaire, using statistical tests of descriptive analysis, inferential analysis, and multivariate analysis. The research found guidelines for future agricultural technology development to increase productivity in the Agricultural sector composed of 4 latent. The most important item of each latent were as following: 1) Agrobiology Technology (= 4.41), in important item as choose seeds that for disease resistance and tolerate the environment to suit the cultivation area, 2) Environmental Assessment (= 4.37),, in important item as survey of cultivated areas according to topography with geographic information system, 3) Agricultural Innovation (= 4.30), in important item as technology reduces operational procedures, reduce the workforce and can reduce operating costs, and 4) Modern Management Systems (= 4.13), in important item as grouping and manage as a cooperative to mega farms. In addition, the hypothesis test found that the difference in manufacturing firm sizes. Medium and Small size and large size revealed overall aspects that were significantly different at the level of 0.05. The analysis of the developed structural equation model found that there was in accordance and fit with the empirical data and passed the evaluation criteria. Its Chi-square probability level, relative Chi-square, the goodness of fit index, and root mean square error of approximation were 0.062, 1.165, 0.961, and 0.018, respectively.

Validation of the Instructional Materials Motivation Survey among Medicine Resident Physicians

Purpose The Instructional Materials Motivation Survey (IMMS) was developed to measure motivational characteristics of a learning activity, building on Keller's Attention, Relevance, Confidence, Satisfaction (ARCS) motivation model. We aimed to validate IMMS scores using validity evidence of internal structure and relations with other variables. Methods Participants were internal medicine and family medicine residents who completed the IMMS following an online module on outpatient medicine, from 2005 to 2009. We used confirmatory factor analysis (CFA) to examine model fit using half the data (split-sample approach). Finding suboptimal fit, we conducted exploratory factor analysis (EFA) and developed a revised instrument. We evaluated this instrument with CFA using the remaining data. Associations were evaluated between IMMS scores and knowledge and other measures of motivation (Motivated Strategies for Learning Questionnaire, MSLQ). All analyses accounted for repeated measures on subjects. Results There were 242 participants. Although internal consistency reliabilities were good (Cronbach alpha ≥0.70), CFA of the original 36-item, 4-domain instrument revealed poor model fit for data sample 1. EFA found that reverse-scored items clustered strongly together. Further EFA using data sample 1, followed by CFA using data sample 2, found good fit for a 13-item, 4-domain model that omitted reverse-scored items (standardized root mean square residual 0.045, root mean square error of approximation 0.066, comparative fit index 0.96). Linear regression confirmed positive, statistically significant associations for most hypothesized relationships, including IMMS total with knowledge (r=0.19) and MSLQ total (r=0.53; both p&lt;.001). Examination of reverse-scored items suggested participant inattention but not acquiescence. Conclusions IMMS scores show good reliability and relations with other variables. However, the hypothesized and empirical factor structures do not align, and reverse-scored items show particularly poor fit. A 13-item, 4-domain scale omitting reverse-scored items showed good model fit.

A longitudinal examination of the measurement properties and invariance of the Sleep Condition Indicator in Chinese healthcare students

BackgroundThe Sleep Condition Indicator (SCI), an insomnia measurement tool based on the updated Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) criteria with sound psychometric properties when applied in various populations, was evaluated here among healthcare students longitudinally, to demonstrate its measurement properties and invariance in this particularly high-risk population.MethodsHealthcare students of a Chinese university were recruited into this two-wave longitudinal study, completing the simplified Chinese version of the SCI (SCI-SC), Chinese Regularity, Satisfaction, Alertness, Timing, Efficiency, Duration (RU_SATED-C) scale, Chinese Patient Health Questionnaire-4 (PHQ-4-C), and sociodemographic variables questionnaire (Q-SV) between September and November 2022. Structural validity, measurement invariance (MI), convergent and discriminant validity, internal consistency, and test–retest reliability of the SCI-SC were examined. Subgroups of gender, age, home location, part-time job, physical exercise, and stress-coping strategy were surveyed twice to test cross-sectional and longitudinal MI.ResultsWe identified 343 valid responses (62.9% female, mean age = 19.650 ± 1.414 years) with a time interval of seven days. The two-factor structure was considered satisfactory (comparative fit index = 0.953–0.989, Tucker–Lewis index = 0.931–0.984, root means square error of approximation = 0.040–0.092, standardized root mean square residual = 0.039–0.054), which mostly endorsed strict invariance except for part-time job subgroups, hence establishing longitudinal invariance. The SCI-SC presented acceptable convergent validity with the RU_SATED-C scale (r ≥ 0.500), discriminant validity with the PHQ-4-C (0.300 ≤ r < 0.500), internal consistency (Cronbach’s alpha = 0.811–0.835, McDonald’s omega = 0.805–0.832), and test–retest reliability (intraclass correlation coefficient = 0.829).ConclusionThe SCI-SC is an appropriate screening instrument available for assessing insomnia symptoms among healthcare students, and the promising measurement properties provide additional evidence about validity and reliability for detecting insomnia in healthcare students.

Cross-cultural adaptation and psychometric evaluation of the Turkish version of the Smombie Scale for Adolescents.

Smombie has become an important problem especially in terms of adolescent health. The aim of this study was to translate the Smombie Scale for Adolescents (SSA) into Turkish and to examine its psychometric properties. This study has a methodological design. The study was conducted between March and April 2024. The sample of the study consisted of 430 adolescents. The data were collected by using Personal Information Form and SSA. Content Validity Index, Confirmatory Factor Analysis (CFA), test-retest reliability, Cronbach's α coefficient, item-total score correlation, 27% upper-lower group item analysis and Hotelling T2 test were used in data analysis. The four-factor structure of the scale showed a good fit in CFA (chi-square minimum discrepancy [CMIN] = 187.463, degrees of freedo (DF) = 83, CMIN/DF = 2.259, root mean square error of approximation = 0.054, root mean square residual = 0.033, goodness of fit index = 0.947, adjusted goodness of fit index = 0.923, normed fit index = 0.930, tucker-lewis index = 0.949 and comparative fit index = 0.959). Cronbach's α coefficient of the scale was found to be 0.86. The item-total score correlation of the scale was found between 0.212 and 0.721. The test-retest intraclass correlation coefficient of the scale was found to be 0.876. This study shows that the scale is a reliable tool for assessing adolescents' smombie tendencies. It is thought that the scale will contribute to the protection and development of adolescent health.

STRATEGIC PLANNING GUIDELINES FOR SUCCESS IN INDUSTRIAL ENTERPRISES

Objective: The objective of this research is to examine the organizational structure and operational characteristics of industrial businesses, investigate components of strategic planning guidelines, and develop a structural equation model, with the aim of achieving sustainable success for industrial enterprises. Theoretical Framework: Content analysis method is a theoretical framework used to examine the presence and concepts of qualitative data. The framework is used to summarize findings and recommendations, from in-depth interviews and focus group discussions, into frequency values. Survey research framework is a structured approach that guides design, implementation, and analysis of surveys to gather data from targeted populations. The framework is used in quantitative research component, to collect and analyze data using descriptive and inferential statistics Method: Qualitative research involved conducting in-depth interviews with 9 experts and facilitating focus group discussions with 11 qualified individuals. Quantitative research is conducted through surveys to 500 industrial business executives, utilizing descriptive statistics, correlation analysis, and multivariate statistics. Results and Discussion: Findings from developed structural equation model indicated good alignment with observational data, with a Chi-square value of 0.094, Chi-square ratio of 1.115, goodness-of-fit index of 0.954, and a root mean square error of approximation of 0.015. Research Implications: Strategic planning is significant in business operations. Well-formulated business strategies will impact managerial efficiency, creating opportunities and enhancing a competitive advantage for industrial enterprises. Originality/Value: Findings revealed four significant factors contributing to success in industrial enterprises, listed in descending order of importance: 1) adaptive skills, 2) digital technology, 3) collaboration, and 4) organizational support.

Associations Between Sociodemographic Characteristics, eHealth Literacy, and Health-Promoting Lifestyle Among University Students in Taipei: Cross-Sectional Validation Study of the Chinese Version of the eHealth Literacy Scale.

The popularization of the internet and rapid development of mobile devices have led to an increased inclination and opportunities to obtain health-related information online. The eHealth Literacy Scale (eHEALS), widely used for measuring eHealth literacy, assesses an individual's ability to search, understand, appraise, and use eHealth information. However, the Chinese version of the eHEALS multiple-factor model remains to be validated, and the correlation between eHEALS and the health-promoting lifestyle profile (HPLP) among university students is rarely explored in Taiwan. This study aimed to examine the fit, validity, and reliability of the Chinese eHEALS multiple-factor model and to clarify the predictive effects of eHEALS on the HPLP among university students. University students in Taipei, the capital of Taiwan, were recruited, and 406 valid questionnaires including sociodemographic characteristics, eHEALS, and HPLP responses were collected. Confirmatory factor analysis was performed to validate the Chinese eHEALS. Independent sample t test, 1-way ANOVA, and multiple linear regression analyses were conducted to examine the relationship between sociodemographic variables and the HPLP. Pearson product-moment correlation and binary logistic regression analyses were performed to ascertain the predictive effects of eHEALS on the HPLP. The Chinese eHEALS exhibited an optimal fit when delineated into the search, usage, and evaluation 3-factor model (comparative fit index=0.991, Tucker-Lewis index=0.984, root mean square error of approximation=0.062), and its validity and reliability were confirmed. The mean eHEALS score of university students was 3.17/4.00 (SD 0.48) points, and the score for the evaluation subscale was the lowest (mean 3.08, SD 0.56 points). Furthermore, there were significant sex, institution orientation, daily reading time, daily screen time, primary information channel, and perceived health status differences in the HPLP: male participants (t404=2.346, P=.02), participants attending general university (t404=2.564, P=.01), those reading ≥1 hour daily (F2,403=17.618, P<.001), those spending <3 hours on mobile devices or computers daily (F2,403=7.148, P<.001), those acquiring information from others (t404=3.892, P<.001), and those with a good perceived health status (F2,403=24.366, P<.001) had a significantly higher score. After adjusting for sociodemographic variables, the eHEALS score remained an independent predictor of the HPLP. Compared to students with relatively high eHEALS scores, those with relatively low eHEALS scores had a 3.37 times risk of a negative HPLP (adjusted odds ratio [OR]=3.37, 95% CI 1.49-7.61), which could explain 14.7%-24.4% of the variance (Cox-Snell R2=0.147, Nagelkerke R2=0.244, P=.004). There is room for improvement in eHealth literacy among university students in Taipei. eHEALS may be used to screen students who require HPLP improvement, thereby providing appropriate eHealth literacy training programs, particularly those targeting evaluation literacy. Additionally, the 3-factor model of the Chinese eHEALS used in this study results in more definite scale content, thus increasing the practicality and applicability of this scale in health-promoting studies.

Psychological distress, health-promoting lifestyle and sociodemographic factors in Honduran university students: a structural equation model.

This study sought to analyze an explanatory model on the relationship among sociodemographic factors, health-promoting lifestyle behaviors and psychological distress (depression, anxiety and stress) in college students. This is an observational, analytical and cross-sectional study conducted on a national sample of 4203 students who entered a macro university in Honduras in 2021, 2022 and 2023. We used a sociodemographic survey, the Health-Promoting Lifestyle Profile (HPLP-II) and the Depression, Anxiety and Stress Scales (DASS-21). Univariate analysis and a multivariate structural equation model were conducted. The average HPLP-II score was 117.45 (± 23.41), and the average DASS-21 score was 20.06 (± 14.16). The multivariate model showed a good data fit (comparative fit index = 0.951; Tucker-Lewis index = 0.957; root mean square error of approximation = 0.067 [90% CI = 0.067-0.068]). Results indicate that being a woman (β = 0.11; p < 0.001) and being enrolled in biological and health sciences (β = 0.09; p < 0.001) significantly predict HPLP-II scores. Furthermore, being a woman (β = 0.17; p < 0.001), age (β = 0.10; p < 0.001) and having pre-existing medical conditions (β = 0.16; p < 0.001) significantly explain part of the variance of DASS-21. A significant reverse relationship between health-promoting behavior and psychological distress was shown (r = -0.36; p < 0.001). This study identifies protective and risky sociodemographic factors linked to health-promoting lifestyle behaviors and psychological distress. Our findings have implications for developing comprehensive intervention policies and strategies to promote health in higher education settings.

Fit Indices in Structural Equation Modeling and Confirmatory Factor Analysis: Reporting Guidelines

This research explores the essential aspects of reporting fit indices in Structural Equation Modeling (SEM), focusing on their significance, methodologies for evaluation, and implications for model validity. The aim is to provide a comprehensive understanding of how fit indices contribute to the rigor and reliability of SEM studies. Methodologically, the study reviews prominent fit indices such as Comparative Fit Index (CFI), Tucker-Lewis Index (TLI), Root Mean Square Error of Approximation (RMSEA), Standardized Root Mean Residual (SRMR), and Chi-Square Test of Model Fit (χ²). Each index is defined, and specific threshold values are discussed to guide researchers in interpreting their findings effectively. Originality in this study lies in synthesizing current literature to emphasize the importance of transparent reporting practices in SEM, enhancing methodological clarity and promoting replicable research outcomes. Contributions include a structured approach to understanding fit indices’ roles in model assessment and validation, aiding researchers in advancing theoretical frameworks with robust empirical support.

Empirical Investigation of Multilayered Framework for Predicting Academic Performance in Open and Distance Learning

Integrating artificial intelligence (AI) in open and distance learning (ODL) necessitates comprehensive frameworks to evaluate its educational implications. Existing models lack a robust multilayered analysis of AI’s impact on educational outcomes in ODL. This study introduces a Multilayered Process Framework designed to predict academic performance in ODL and enhance inclusivity, aligning with UNESCO’s 2030 educational goals. The current research employed structural equation modelling (SEM) to analyse the impact of AI adoption, focusing on the initial layers of the process framework. Preliminary validation of the SEM framework showed a good model fit, with a Chi-square/df ratio of 2.34, Root Mean Square Error of Approximation (RMSEA) of 0.045, and Comparative Fit Index (CFI) of 0.97, indicating the model’s effectiveness in capturing the complexities of AI impacts on student outcomes. This framework provides a structured, multilayered approach to understanding AI’s role in education, facilitating the development of equitable and accessible AI-driven educational technologies. It lays the foundational work for expanding research into predictive analytics with a support vector machine (SVM), aiming to universalise quality education and ensure global educational equity. This study highlights the practical implications for integrating AI in educational settings and suggests future research directions to enhance the adaptability and effectiveness of AI-driven educational interventions.

Psychometric Properties of the Persian Version of the Intensive Care Experience Questionnaire (ICE-Q).

Background and Purpose: It is important to assess the experience of patients who have been admitted to an intensive care unit to provide the best treatment and nursing care possible. Therefore, a valid and reliable tool is necessary for measurement. This study aimed to determine the psychometric properties of the Persian version of the Intensive Care Experience Questionnaire (ICEQ) for open-heart surgery patients. Methods: The study was conducted in four steps: translation, face and content validity, confirmatory factor analysis, and reliability assessment. The adapted questionnaire was administered to 200 Iranian cardiac surgery patients who had received treatment in an intensive care unit within the past month. Results: In the final Persian version of ICEQ, there are 4 factors and 21 items. Following the translation and cultural adaptation process, the content validity was evaluated. Three items had content validity ratio < 0.6, so they were deleted. Scale-level content validity index/Average was 0.81 and more than 0.7 for each item on the scale. This scale was validated through confirmatory factor analysis using fit indicators (comparative fit index, normalized fit index, root mean square error of approximation, and chi-square). There was Cronbach's alpha of 0.71-0.85, and intraclass correlation coefficients were 0.82-0.93 for subscales. Conclusions: The Persian version of ICEQ showed appropriate psychometric properties. This scale may be useful to inform the development of effective interventions to improve subsequent outcomes for Iranian open-heart surgery patients.

Validation and Refinement of the Sense of Coherence Scale for a French Population: Observational Study.

Salutogenesis focuses on understanding the factors that contribute to positive health outcomes. At the core of the model lies the sense of coherence (SOC), which plays a crucial role in promoting well-being and resilience. Using the validscale Stata command, we aimed to assess the psychometric properties of the French version of the 3-dimension 13-item SOC questionnaire (SOC-13), encompassing the comprehensibility, manageability, and meaningfulness dimensions. We also aimed to determine if a refined scale, assessed through this method, exhibits superior psychometric properties compared to the SOC-13. A sample of 880 consecutive primary care patients recruited from 35 French practices were asked to complete the SOC-13. We tested for internal consistency and scalability using the Cronbach α and Loevinger H coefficients, respectively, and we tested for construct validity using confirmatory factor analysis and goodness-of-fit indices (root mean square error of approximation [RMSEA] and comparative fit index [CFI]). Of the 880 eligible patients, 804 (91.4%) agreed to participate (n=527, 65.6% women; median age 51 years). Cronbach α and Loevinger H coefficients for the SOC-13 were all <0.70 and <0.30, respectively, indicating poor internal consistency and poor scalability (0.64 and 0.29 for comprehensibility, 0.56 and 0.26 for manageability, and 0.46 and 0.17 for meaningfulness, respectively). The RMSEA and CFI were >0.06 (0.09) and <0.90 (0.83), respectively, indicating a poor fit. By contrast, the psychometric properties of a unidimensional 8-item version of the SOC questionnaire (SOC-8) were excellent (Cronbach α=0.82, Loevinger H=0.38, RMSEA=0.05, and CFI=0.97). The psychometric properties of the 3-dimension SOC-13 were poor, unlike the unidimensional SOC-8. A questionnaire built only with these 8 items could be a good candidate to measure the SOC. However, further validation studies are needed before recommending its use in research.

Assessment of psychometric performance for the Chinese version of the Brief Inventory of Perceived Stress integrating exploratory graph analysis and confirmatory factor analysis.

This study was to evaluate measurement properties of the Chinese version of the Brief Inventory of Perceived Stress (BIPS-C) and confirm possible solutions for measuring the constructs underlying perceived stress. A total of 1356 community residents enrolled and were randomly split into two halves. The first half was used to explore the underlying constructs of the BIPS-C by exploratory graph analysis (EGA) and the second half was used to compare and confirm the constructs by confirmatory factor analysis (CFA). The EGA identified a one-factor model of the BIPS-C with an accuracy of 99.3%. One-factor, three-factor, second-order, and bifactor models were compared by CFAs. The bifactor model with one general and three specific factors was found to be the most adequate [comparative fit index (CFI) = 0.990; Tucker-Lewis index (TLI) = 0.979; root mean square error of approximation (RMSEA) = 0.058] and was superior to the other models. The related bifactor indices showed a stronger existence of the general factor. The bifactor model of the BIPS-C also showed adequate internal consistency with McDonald's omega and omega subscales ranging from moderate to strong (0.677-0.869). The BIPS-C demonstrates sufficient measurement properties for assessing general perceived stress.

Development and validation of the metaverse perception scale for nursing students

BackgroundThe use of Metaverse applications in nursing education is increasing every day and the evaluation of nursing students' perceptions of this new digital technology may guide interventions related to the use of the Metaverse. However, currently, no standardized instrument specifically designed to measure nursing students' perceptions of the Metaverse exists in Turkey. AimTo develop and validate the Metaverse Perception Scale for Turkish nursing students. MethodThis methodological study was carried out between March 1, 2023 and June 30, 2023 and its sample consisted of 770 nursing students who were enrolled in undergraduate nursing departments of universities in Turkey. The item pool was created based on a literature review and data were analyzed using descriptive statistics, item analysis, exploratory and confirmatory factor analysis, convergent and divergent validity, correlation analysis, internal consistency reliability and test-retest analysis. ResultsThe content validity index for the items ranged between 0.85 – 1.00. According to exploratory factor analysis, the eigenvalue of four factors was greater than one. These four factors explained 77.28 % of the total variance. In the scale model developed for this study, model fit was found to be acceptable for goodness of fit index:.921 and root mean square error of approximation:.064. χ2/sd: 1.659, normalized fit index:.961 and chi-square/degree of freedom revealed that model fit was at a good level and within the recommended value ranges. It was determined that the scale showed convergent and divergent validity and Cronbach's Alpha value ranged between 0.95 and 0.93 in the subscales. The Metaverse Perception Scale in Nursing Students was found to have a high level of test-retest reliability. ConclusionThis study showed that the scale, which consists of 24 items and four subscales, is a valid and reliable measurement tool that can be used to assess nursing students' perceptions of the Metaverse in the Turkish context. This scale can contribute to the evaluation of Turkish nursing students' perceptions of the Metaverse, as well as the effective management of processes related to Metaverse practices.