No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Structural Model Evaluation And Modification - An Interval Estimation Approach
Multivariate Behavioral Research
... We conducted CFA using IBM SPSS Amos, version 25.0. The model fit was measured through the following indices: ratio of the Chi-Square to degrees of freedom (χ 2 /df); Comparative Fit Index (CFI) [43], which can take values from the 0 to 1 range; values of .90 or greater indicate of a goodfitting model [43,44]; Root Mean Square Error of Approximation (RMSEA) [45], whose values .05 or lower indicate excellent model fit, values .08 are acceptable, and values greater than .10 show an unacceptable model [46,45]; Standardized Root Mean Square Residual (SRMR) [47], that has to be less than .08 ...
... The model fit was measured through the following indices: ratio of the Chi-Square to degrees of freedom (χ 2 /df); Comparative Fit Index (CFI) [43], which can take values from the 0 to 1 range; values of .90 or greater indicate of a goodfitting model [43,44]; Root Mean Square Error of Approximation (RMSEA) [45], whose values .05 or lower indicate excellent model fit, values .08 are acceptable, and values greater than .10 show an unacceptable model [46,45]; Standardized Root Mean Square Residual (SRMR) [47], that has to be less than .08 [47]; Goodness of Fit Index and Adjusted Goodness of Fit Index (GFI and AGFI), whose values are acceptable if up to .90 [47]. ...
... and the CFI of ≥ -.010 can be interpreted as a lack of invariance [64,65]. Moreover, we tested model fit using the Comparative Fit Index (CFI) [43], which values of .90 or greater indicate a good-fitting model [43,44]; Root Mean Square Error of Approximation (RMSEA) [45], regarding which a value of .05 or less indicate very good model fit, a value of .08 shows acceptable fit and a value greater than .10 shows an unacceptable model [46,45]; Standardized Root Mean Square Residual (SRMR), that has to be less than .08 to indicate a good model [47]. ...
Introduction: This research paper aims to validate the Work-related Acceptance and Action Questionnaire (WAAQ, Bond et al., 2013) in the Italian context, demonstrating gender invariance. This measure was developed to address the need for a brief contextual measure of psychological flexibility in professional domains. Methods: Five studies were conducted. In Study 1, the scale was culturally adapted; parallel analysis and Exploratory Factor Analysis were conducted. Study 2 tested the structure, and the model fit of the 7-item scale through confirmatory factor analysis and internal consistency indices. Study 3 examined concurrent validity. Study 4 verified the temporal reliability using the test-retest method. Study 5 analyzed gender invariance. Results: In Study 1, the scale confirmed its one-factorial structure, accounting for 59.73% of the variance. Study 2 demonstrated a good model fit of the 7-item scale in the Italian context. Study 3 showed negative correlations with psychological inflexibility and positive correlations with life satisfaction, flourishing, and work engagement. Study 4 verified the temporal stability of the scale. Study 5 confirmed configural, metric, scalar, and residual invariance regarding gender. Discussion: Overall, the results support the WAAQ's validity and reliability for assessing work-related psychological flexibility, making it a valuable tool for researchers and practitioners.
... DFA'da ²/df raporlaması standart bir uygulama olsa da hangi uyum indekslerinin raporlanması gerektiği konusunda literatürde kesin bir fikir birliği bulunmamaktadır (İlhan & Çetin, 2014). Ki-kare testi ( ²) örneklem büyüklüğünden önemli ölçüde etkilendiğinden, modelin değerlendirilmesindeki-kare/serbestlik derecesi ( ²/df) oranının kullanılması önerilmektedir (Şimşek, 2007 Steiger, 1990 Modelin Uyum Değerlendirmesi DFA'dan elde edilen uyum indeksleri, test edilen modelin veriyle iyi derecede uyum sağladığını göstermektedir. 2/ oranı 1.94 olarak hesaplanmış olup, 2'nin altındaki değerler iyi uyumu gösterdiğinden modelin güçlü bir yapısal uyuma sahip olduğu söylenebilir (Byrne, 2010;Schermelleh-Engel et al., 2003). ...
... RMR değeri 0.034 olup, 0.05'in altında olduğu için mükemmel uyum gösterdiği söylenebilir. RMSEA değeri 0.059 olup, 0.05 ile 0.08 aralığında olduğu için kabul edilebilir uyum sınırları içinde yer almaktadır (Steiger, 1990). ...
Bu çalışma, ilkokul 2., 3. ve 4. sınıf öğrencilerinin ideal vatandaşlık eğilimlerini ölçmeye yönelik geçerli ve güvenilir bir ölçek geliştirmeyi amaçlamaktadır. Vatandaşlık eğitimi, bireylerin topluma etkin katılım sağlamalarını, sorumluluk bilinci geliştirmelerini ve demokratik değerlere sahip bireyler olarak yetişmelerini destekleyen kritik bir süreçtir. Ancak ilkokul öğrencilerine yönelik bütüncül bir vatandaşlık ölçeğinin eksikliği, bu alanda yeni bir ölçme aracının geliştirilmesini gerekli kılmaktadır.
Araştırma sürecinde, kapsamlı bir literatür taraması yapılmış ve ideal vatandaşlık eğilimini ölçmeye yönelik 30 maddelik bir taslak ölçek oluşturulmuştur. Bu taslak, alan uzmanlarının görüşleri doğrultusunda değerlendirilmiş ve 20 maddeye indirgenmiştir. Ölçeğin yapı geçerliliğini test etmek için Açımlayıcı Faktör Analizi (AFA) gerçekleştirilmiş ve ölçeğin tek faktörlü bir yapıya sahip olduğu belirlenmiştir. Faktör yükleri ,646 ile ,861 arasında değişmekte olup, ölçeğin geçerli bir yapıya sahip olduğunu göstermektedir. Ayrıca, Cronbach’s Alpha iç tutarlılık katsayısı 0,92 olarak hesaplanmış, bu da ölçeğin yüksek güvenilirliğe sahip olduğunu kanıtlamaktadır.
Doğrulayıcı Faktör Analizi (DFA) sonuçları, modelin veriyle yüksek derecede uyum sağladığını göstermektedir. Bu bulgular doğrultusunda geliştirilen ölçek, ilkokul öğrencilerinin vatandaşlık eğilimlerini ölçmek için geçerli ve güvenilir bir ölçme aracı olarak değerlendirilmektedir. Ölçeğin eğitim politikalarına, öğretim programlarına ve vatandaşlık eğitimi araştırmalarına katkı sağlaması beklenmektedir.
... RMSEA measures the discrepancy between the implied model and the observed covariance matrix per degree of freedom, with lower values indicating better fit. In this case, a value of 0.001 suggests that the model fits the data extremely well, with very little error between the model's predicted relationships and the actual relationships observed in the data (Steiger, 1990). The SRMR of 0.232 suggests a weak good fit between the proposed structural equation model (SEM) and the observed data. ...
... RMSEA measures the discrepancy between the implied model and the observed covariance matrix per degree of freedom, with lower values Onyebuchi Iwegbu, Ndubuisi Chidi Olunkwa, Isaac Chiawolam Nwaogwugwu, Anthonia T. Odeleye, Ernest Simeon Odior and Ndubisi Ifeanyi Nwokoma indicating better fit. In this case, a value of 0.001 suggests that the model fits the data extremely well, with very little error between the model's predicted and actual relationships observed (Steiger, 1990). The SRMR of 0.084 suggests a reasonably good fit between the proposed structural equation model (SEM) and the observed data. ...
Deficits in basic infrastructure have been acknowledged as one of the challenges of local communities globally and this is quite relevant in the Southwestern Nigeria. Due to shortage of government funding, infrastructural deficit has continued to limit developments in Osun and Oyo states. Hence, communities’ resort to the use of user fees in addressing the funding gap. This study examines the effect of user fees on community development in these selected states. The study employs structural equation model (SEM) to analyze the research objective among 3,672 households. The result suggests that informal user fees have a negative and significant effect on the extent of community development in Osun and Oyo States, although, the willingness to pay by households has a positive effect on community development projects. The study recommends joint collaboration of local community leaders, Community Development Associations (CDA) and community members towards contribution of user fees and monitoring of same to enhance and fast track community development projects. JEL Classification: H20, H21, H72
... During the model fit evaluation, we used the Comparative Fit Index (CFI) [40], Tucker-Lewis Index (TLI) [41], Root Mean Square Error of Approximation (RMSEA) [42], and Standardized Root Mean Squared Residual Index (SRMR) [43]. We adhered to conventional thresholds recommended to signify a well-fitting model: CFI and TLI values of 0.95 or above and RMSEA and SRMR values of 0.08 or below [43,44]. ...
... Lastly, a bifactor model with a general factor of the real relationship and two specific factors of genuineness and realism was fitted. The CFA model showed acceptable indices of fit: χ² [42] ...
The current study assessed the psychometric properties of the long (24 items) and brief (12 items) versions of the Real Relationship Inventory–Client (RRI-C) in a United States sample. The RRI-C is the most used quantitative measure of the real relationship construct, yet its psychometric properties have not been explored outside its development studies. A sample of 700 adults in individual psychotherapy was recruited in the study and filled out a comprehensive battery of measures. Analytical techniques included confirmatory factor analysis (CFA), exploratory structural equation modeling (ESEM), multigroup CFA, multigroup factor analysis alignment, item response theory, internal reliability assessments, Bland-Altman regression analysis, and calculation of reliable change benchmark thresholds. Both RRI-C versions demonstrated a bifactor structure encompassing Genuineness and Realism dimensions. The bifactor ESEM model provided strong fit: χ²[210] = 482.464, CFI = 0.999, TLI = 0.998, RMSEA = 0.043, SRMR = 0.020 for the 24-item RRI-C; χ²[45] = 111.916, CFI = 0.999, TLI = 0.998, RMSEA = 0.046, SRMR = 0.028 for the 12-item RRI-C. McDonald’s omega total was 0.97 and 0.95 respectively. The correlation between the total scores of the two versions was r = 0.98; the average discrepancy was 1.85 points higher for the comprehensive version with a slope of -0.013 (p = 0.12). Both versions showed functionally identical reliability and factor structure when therapy is online vs. in-person. Significant correlations were found between the RRI-C and the Working Alliance Inventory (r = 0.68 and r = 0.67 for the 24-item and 12-item versions, respectively, both p < .001) and the Session Evaluation Scale (r = 0.62 and r = 0.58, respectively, both p < 0.001). This study substantiates the sound psychometric properties of the 24-item and 12-item RRI-C.
... We report fit indices with the following cut-offs for good model fit: the Root mean square error of approximation =<0.06 (RMSEA; Steiger, 1990) and the standardized root mean square residual (SRMR) <0.10 for good and <0.05 for very good fit (Steiger, 1990), comparative fit index (CFI) and Tucker-Lewis index (TLI) >0.95. All models were run in Mplus v8.3 (Muthén and Muthén, 2017), using the robust maximum likelihood estimator (MLR) and the outputs integrated with the R package MplusAutomation (Hallquist and Wiley, 2018). ...
... We report fit indices with the following cut-offs for good model fit: the Root mean square error of approximation =<0.06 (RMSEA; Steiger, 1990) and the standardized root mean square residual (SRMR) <0.10 for good and <0.05 for very good fit (Steiger, 1990), comparative fit index (CFI) and Tucker-Lewis index (TLI) >0.95. All models were run in Mplus v8.3 (Muthén and Muthén, 2017), using the robust maximum likelihood estimator (MLR) and the outputs integrated with the R package MplusAutomation (Hallquist and Wiley, 2018). ...
White matter (WM) tracts of the reward, limbic, and autonomic systems implicate the hypothalamus, nucleus accumbens, ventral tegmental area and the amygdala and are associated with autism, ADHD, addiction and obesity. However, since most of these structures remain uncharacterised in vivo in human neonates, re- search on the early-life predispositions to these long-term "mind and body" conditions and the impact of common fetal exposures such as maternal obesity remains limited. Through the developing human connectome project, we acquired 3T brain diffusion and structural magnetic resonance imaging from healthy neonates born at-term to 137 normal-weight women (controls) and to 28 obese women and scanned at mean 40 weeks+6 days (+/-9 days) postmenstrual age (PMA). We first developed novel tractography protocols to reconstruct anatomical WM pathways for the neonatal medial forebrain bundle, ventral amygdalofugal pathway, amygdalo-accumbens fasciculus, stria terminalis and autonomic dorsal longitudinal fasciculus (DLF). We then quantified WM structure from the mean tract fibre bundle density (FD) and fibre cross-section (FC) and using regression path models evaluated WM change across PMA and the effects of antenatal obesity exposure and neonatal covariates. Lastly, we explored if neonatal WM FD and obesity exposure predicted child psycho-cognitive outcomes and anthropometry at 18 months. We show successful in vivo tractography of tracts with high topographical correspondence to adult histology, including in subcompartments of the hypothalamus and amygdala. The obesity exposure*PMA interaction was significant for mean FD in the bilateral amygdalo-accumbens fasciculus and right uncinate fasciculus. Males had larger FC in these same tracts bilaterally. Antenatal obesity exposure predicted lower cognitive scores and higher WHO weight and height z-scores at 18 months. Toddler reward-seeking temperament was correlated with higher weight z-score and was predicted by higher neonatal FD of the amygdalo-accumbens and uncinate fasciculi. Denser neonatal DLF predicted higher language and cognitive scores and fewer autistic traits at 18 months. In conclusion, we inform on neuroanatomical growth in vivo of discrete multisystemic regulatory networks and present evidence for early-life predispositions to psychological outcomes and obesity.
... To verify the general adequacy of the models, indices were compared with the acceptable threshold (Schermelleh-Engel et al., 2003). The model fit was verified using the Satorra-Bentler scaled chi-square test (SBχ 2 ; Satorra & Bentler, 2001), comparative fit index (CFI; Bentler, 1990), root-mean-square error of approximation (RMSEA; Steiger, 1990), standardized root-mean-square residual (SRMR; Hu & Bentler, 1999). To compare the two models, we used the Akaike information criterion (AIC; Burnham & Anderson, 2004). ...
... The interpretation of the RMSEA index follows these indications: a value of .05 or less indicates a very good model fit; a value of .08 shows an acceptable fit, and a value greater than .10 shows an untenable model (Browne & Cudeck, 1993;Steiger, 1990). The SRMR is considered good when it is below .08 (Hu & Bentler, 1999). ...
The aim of this paper was to validate and examine the psychometric properties of the 9-item Temporal Satisfaction With Life Scale (TSWLS) in the Italian context. Four studies were conducted. In Study 1, we performed an exploratory factor analysis. The 3-factor structure-past life satisfaction, present life satisfaction, and future life satisfaction-was confirmed. In Study 2 we tested the structure of the nine items of the scale, based on confirmatory factor analysis. The 3-factor structure with a high-order factor was the best factorial solution. In Study 3 we tested the concurrent validity of the TSWLS. The scale was significantly and positively related with life satisfaction, flourishing, and positive affects, and negatively related with negative affects. In Study 4 we showed the stability of the TSWLS using the test-retest method after an interval of four weeks.
... Lastly, the Root Mean Square Error of Approximation (RMSEA = 0.060) is below the threshold of.08, further supporting good model fit (Steiger, 1990). Taken together, these indices confirm that the model adequately represents the observed data, with only minor deviations in AGFI and NFI (Figure 3). ...
The study aims at gaining insights into relationships between perceived institutional support and students’ perceptions of AI-supported learning. It also investigates the mediating role perceived learning outcomes and moderating effect of technology self-efficacy within this context. Research model was developed and validated based on Social Cognitive Theory (SCT) and the learning outcomes of students. Using quantitative research design and convenience sampling technique, 204 students from higher education institutions were included in the analysis. Data were analyzed using structural equation modeling (SEM) to test the hypothesized relationships. The results revealed that perceived institutional support significantly impacts students’ perceptions of AI-supported learning ( β = 0.200, C.R. = 2.291, p = 0.022), technology self-efficacy ( β = 0.492, C.R. = 9.671, p < 0.001), and learning outcomes. Additionally, technology self-efficacy was found negative moderating effect ( β = −0.146, CR = −2.507, p = 0.012) the relationship between perceived institutional support and AI-supported learning perceptions. Perceived learning outcome partial mediated the relationship between perceived institutional support and students’ perceptions of AI-supported learning, with a direct effect of ( β = 0.155, p < 0.001) and an indirect effect of ( β = 0.539, p < 0.001), as evidenced by the confidence interval [0.235, 0.549]. These findings highlight the significant interplay of perceived institutional support, technology self-efficacy, and perceived learning outcomes in shaping students’ perceptions of AI in higher education, underscoring the importance of fostering supportive academic environments for effective AI integration. The theoretical and practical implications of the study are discussed.
... Although TLI is slightly lower than the acceptable criteria of 0.900, other indicators all indicate good model fit. CFI is higher than 0.900, both RMSEA and SRMR are less than 0.080 (Hu and Bentler, 1999;Schreiber et al., 2006;Steiger, 1990). ...
Introduction
To enhance competitiveness, numerous organizations have introduced control and penalty systems to manage employee work errors. However, these systems have often backfired, negatively impacting employees’ emotions and behaviors. Recognizing the critical role of leadership in error management, this study examines how leaders’ tolerance of their followers’ mistakes influences employees’ work engagement, drawing on Affective Events Theory (AET).
Methods
Analyzing data from 435 front-line public health service staff, this study investigates the relationship between leader tolerance and employees’ work engagement. First, the Harman one-factor test was employed to assess common method variance (CMV) in the research data. Second, the reliability and validity of the data were evaluated using the Cronbach’s α, KMO, AVE, CR, and CFA. Finally, the proposed mediating hypotheses were tested using Model 6 in the SPSS Process macro (version 4.1).
Results
We found that leader tolerance significantly boosts employees’ work engagement. Furthermore, our results confirm the mediating roles of perceived organizational support (POS) and organizational identification in the relationship between leader tolerance and work engagement. This study also validates the hypothesized chain mediation model, demonstrating how POS and organizational identification together mediate the influence of leader tolerance on employees’ work engagement.
Discussion
These results underscore the importance of leadership styles that accommodate employees’ errors and emphasize the crucial roles of organizational support and identification. The findings highlight the need for organizations to adopt more supportive leadership approaches rather than relying solely on control and penalty systems. The study concludes by stating the theoretical and practical implications, along with recommendations for future research on leader tolerance.
... The criterion suggested that acceptable model fit for Comparative Fit Index scores is .90 or greater (Bentler, 1995;Hoyle, 1995;Tabachnick & Fidell, 19961, and the Root Mean Square Error of Approximation (Steiger, 1990) value of .05 or lower was interpreted as indicating a good fit. Values up to .08 indicated an acceptable fit (Browne & Cudeck, 1993). ...
The purpose of the present study was to investigate the factorial validity of the Brunel Mood Scale, which measures anger, confusion, depression, fatigue, tension, and vigor, for water-skiers. Participants were 345 water-skiers (age range 16 to 39 years, men: n = 311, women: n = 34) who completed the scale approximately 1 hour before a water-skiing competition. Confirmatory factor analysis indicated support for the validity of the 6-factor model, with a Comparative Fit Index of .90 and Root Mean Squared Error of Approximation of .07. Internal consistency coefficients were above the .70 criterion. It is suggested that the Brunel Mood Scale shows factorial validity for use with water-skiers and that researchers should continue to assess validation of the Brunel Mood Scale with other measures and with specific appropriate samples.
... Descriptive fit was also evaluated, considering that S-B χ 2 is sensitive to sample size and can falsely reject an adequate model. The comparative fit index (CFI) [87], the root mean square error of approximation (RMSEA) [88]. and the standardized root mean residual (SRMR) [89] were also employed to evaluate descriptive fit. ...
This paper describes the simultaneous co-development of Oral Health Behavior Social Support (OHBSS) scales in English and Spanish. OHBSS scales assess social support for toothbrushing, flossing, and dental care utilization, which are targets for interpersonal-level interventions to promote oral health among Hispanic/Latino adults. The focus was on Mexican-origin adults, who comprise the largest United States Hispanic/Latino subgroup and experience a high oral disease burden. All participants self-identified as Mexican-origin adults (ages 21–40 years old), living along the California-Arizona-Mexico border. Independent samples were recruited for each study partnering with Federally Qualified Health Centers. First, we conducted semi-structured interviews about social support for oral health behaviors in August to November 2018 (Study 1, N = 72). Interviews were audio recorded, transcribed (in original language, Spanish or English), and qualitative data were coded and analyzed in Dedoose following three topical codebooks; excerpts were used to co-create the large bilingual item data bank (OHBSSv1). The item bank was pre-tested via 39 cognitive interviews between December 2019 to March 2020, reviewed by an expert panel with several bilingual members, reduced to 107 Spanish/109 English items (OHBSSv2), then pilot tested in January to December 2021 (Study 2, N = 309). Pilot survey data were analyzed through Exploratory Factor Analysis and Horn’s parallel analysis, overall and by language, to examine response patterns and inform item selection (OHBSSv3). The scales queried social support for toothbrushing, flossing, and dental care utilization across 39 items from three sources (family, health providers, others/friends), plus up to nine optional dental care-related items (Study 3, conducted April 2022 to February 2023, N = 502). Confirmatory Factor Analysis (CFA) assessed model fit, overall and by language (multiple group CFA). Final OHBSS scales include 37 items, plus seven optional items. Acceptable model fit for three-factor structures for each oral health behavior was found, providing evidence of the scales’ construct validity. Cronbach’s alphas and McDonald’s omegas were tabulated; all were above 0.95, overall and by language, supporting scales’ internal consistency.
... Through this approach, we aimed to provide a comprehensive and detailed analysis of model fit to support our research hypotheses and model selection. As illustrated in Table 5, Model 1 displayed a Chi-square/df ratio of 6.4, suggesting potential overcomplexity in the model, although NFI and CFI values near 1 indicated good relative improvement compared to the baseline model 32,36 . GFI and AGFI values suggested a relatively good fit, and an RMSEA value at the upper limit of the acceptable range further qualifies this assessment 37 . ...
Antimicrobial resistance is a critical global health challenge, requiring effective strategies to promote rational antimicrobial prescribing among healthcare professionals. This study investigates how social support mediates prescribing behavior through psychosocial factors, providing insights into healthcare decision-making. A cross-sectional survey of 720 healthcare professionals was conducted, and Structural Equation Modeling (SEM) was used to evaluate the mediating roles of self-efficacy, knowledge and skills, and health beliefs. The results identified significant mediating pathways, emphasizing the role of social support in shaping prescribing intentions and promoting rational drug use. These findings offer actionable recommendations for healthcare policy and antimicrobial stewardship programs by highlighting the importance of fostering supportive environments to enhance decision-making in clinical practice.
... Model fit was assessed using comparative fit index (CFI; Bentler, 1990), non-normed fit index (NNFI; Bentler & Bonett, 1980), root mean square error of approximation (RMSEA; Steiger, 1990), standardized root mean square residual (SRMR; Hu & Bentler, 1999), and the Akaike information criterion (AIC; Akaike, 1974). The chi-square (χ 2 ) test of model fit is reported; however, it was not used to interpret model fit due to its hypersensitivity to factors such as sample size (Gu et al., 2020;Kline, 2016). ...
Objectives
There are ongoing debates regarding how compassion is operationalized and measured. The Compassionate Engagement and Action Scales (CEAS) and the Sussex-Oxford Compassion Scales (SOCS) are based on distinct theoretical models with promising empirical support. This study translated the CEAS and SOCS from English to German and validated their psychometric properties in a German-speaking community sample.
Method
The CEAS and SOCS were translated in a five-stage process including consultation with authors of the original English scales. Participants were recruited online (n = 560) and completed the translated measures as well as questionnaires assessing self-compassion, uncompassionate self-responding, empathic concern, mindfulness, attachment insecurity, depression/anxiety, perceived stress, and mental well-being. Confirmatory Factor Analysis (CFA) was used to assess structural validity, as well as multi-group CFA to assess measurement invariance, and Spearman correlations to assess convergent validity.
Results
Factor analysis results support the models proposed by scale authors for the CEAS-SC, CEAS-FROM, and SOCS-S. Alternative models are proposed for measures assessing compassion for others (CEAS-TO and SOCS-O). Measurement invariance is supported across age, gender, and education level. Internal consistency and convergent validity results support the use of total and subscale scores for all translated measures.
Conclusions
The proposed German versions of the CEAS and SOCS provide valid measures for use with German-speaking populations.
... (Browne & Cudeck, 1993) and even better is less than .05 (Steiger, 1990). In addition, the standardized root-mean-square residual (SRMR) should be less than .08, ...
In a contemporary context where technologies are often (a) crucial venues for adolescent development, sociality, and civic engagement and (b) designed with features that encourage continued use, we ask: How can we assess positive technology use among contemporary adolescents? Using rigorous psychometric methods, we developed a self-report Tech With Care Index among adolescents (ages 13–17) and validated score interpretations. Participants completed two waves of an online survey with the Tech With Care Index, mindfulness measures, intrapersonal and interpersonal measures, and media and technology use measures. After exploratory and confirmatory factor analyses, the final scale included 17 items with four factors: two self-defeating uses (mindless, unhealthy) and two other-benefitting uses (empathic, civic). Subscale scores had reasonable internal reliability, were related to existing mindfulness measures, correlated in predictable ways with other outcomes (e.g., mental health, self-control, empathy, and prosocial behavior), and had high test–retest reliability. The Tech With Care Index addresses the psychological and physical aspects of one’s digital engagement (caring for self) and attention beyond oneself to social and civic considerations (caring for others). It contributes to a growing literature on positive technology, providing a tool for researchers and practitioners to assess and attempt to build thoughtful and prosocial technology use.
... To assess the model fit, we relied on the comparative fit index (CFI; acceptable > 0.90, good > 0.95), root mean square error of approximation (RMSEA; acceptable < 0.08, good < 0.05; Steiger, 1990), and standardized root mean square residual (SRMR; acceptable < 0.08, good < 0.05) values. We used a bootstrapping technique (N = 5000) and 95% confidence intervals (CIs) to determine the significance of the (moderated) mediation effect. ...
Internet addiction has been associated with decreased prosocial behavior in adolescents, and minority studies have investigated the underlying mechanisms involved. This study aimed to examine the mediating effects of self-control and the moderating effects of peer rejection. A longitudinal study with two waves (6 months apart) was used to measure internet addiction (T1), peer rejection (T1), self-control (T1/T2), and prosocial behavior (T1/T2) among 1048 secondary school students (Mage = 14.80 years old, SD = 1.61) in a southern Chinese metropolitan area. A longitudinal path analysis model was applied to analyze the data and derive insights about the relationships between these variables. The findings indicated that T1 internet addiction negatively influenced later prosocial behavior through reduced self-control, particularly among adolescents with lower levels of peer rejection. These findings clarify how internet addiction impairs prosocial development, and we propose a framework for intervention: mitigating peer rejection and harnessing self-control as a mediator to counteract the adverse effects of internet addiction.
... Per quanto riguarda la scelta degli indici da utilizzare per la misura della bontà di adattamento dei modelli, al fine di pervenire ad una valutazione non inficiata da fattori di disturbo, quali la numerosità campionaria, si è preferito aggiungere al test χ 2 il calcolo di ulteriori indici di adeguatezza ( (Steiger, 1990) con il 90% di intervallo di fiducia: valori di SRMR compresi tra .05 e .10 ...
Background: Although numerous studies have been done on the topic of job satisfaction, as regards the Italian research, the construction of specific psychometric instruments is lacking. Objectives: The present paper is aimed to develop a scale to measure job satisfaction referring to our cultural context. Methods: Participants were 222 workers (36.5% males, 63.5% females) with an average age of 38.39 years (SD = 10.91). The formulated items were selected from a large item pool on the basis of the evaluation by a group of expert judges, and the item analysis procedure. In order to establish test validity, the following instruments were also administered: Occupational Stress Indicator, Satisfaction With Life Scale, Rosenberg Self-Esteem Scale, Multidimensional Scale of Perceived Social Support, and Beck Depression Inventory. Results: Both exploratory and confirmatory factor analyses highlighted a 6-factor structure. Those factors were responsible for 51.30% of the total variance. Reliability analyses indicated satisfying internal consistency (ranging from a = 73 to a = .86). Construct validity was supported by results obtained calculating correlations with the theoretically associated variables. Conclusions: Our findings suggest promising psychometric properties for the presented measure. The instrument could be used in specific programs developed to promote well-being conditions in work settings.
... Multiple indices were used to assess the model fit while testing both the measurement and structural models, including Chi-square to df ratio or c 2 /df, the comparative fit index (CFI) (40), Tucker-Lewis index (TLI) (41), root mean square error of approximation (RMSEA) (42), and standardized root mean square residual (SRMR) (43). The hypothesized model was tested using R software version 3.5.1 and the Lavaan package (44). ...
The prevalence and effects of cyberbullying are well-established, while there is sparse evidence addressing the experiences of those in vocational schools. Social capital and self-efficacy have attracted significant public and scholarly interest, but research on these factors in cyberspace remains limited in scope. This study aims to comprehensively investigate the pathways through which online social capital and Internet self-efficacy mediate the development of mental health consequences among adolescent cyberbullying victims. A total of 1,716 students in Grades 8-12 from public and vocational schools in China participated in the study. Structural equation modeling (SEM) was applied to specify the relationships between online social capital, Internet self-efficacy, cyberbullying, and mental health problems. Results showed that 12.12% of students reported themselves as cyber bully-victims. Internet self-efficacy could potentially mediate the effects of cyberbullying victimization and mental health problems in both school settings. Online social capital and Internet self-efficacy play mediating roles in the relationship between cyberbullying and mental health problems in public school samples. No significant effect of online social capital was found in the vocational school sample. The findings provide insights for proactive intervention in developing adequate online social capital and Internet self-efficacy training for cyberbullying prevention. Discussions on differentiated interventions for vocational school students are also presented to inspire future research and practice.
... We then tested the two-factor structure proposed by Metin et al. (2016Metin et al. ( , 2020 for the subscales. While this model improved the fit indices, some indices-particularly RMSEA-remained below acceptable thresholds, which should be under 0.08 and over 0.05 (Steiger, 1990) (Table A1). Upon reviewing the factor loadings, we decided to remove item PAWS_7 ("I take long coffee breaks") from the soldiering subscale. ...
Abstract: (1) Background: Workplace procrastination leads to missed deadlines and financial losses, necessitating a deeper understanding of its risk factors and inhibitors for effective interventions. This study aims to bridge the significant gap in the literature regarding the effects of Authentic Leadership (AL) on workplace procrastination behaviors, including soldiering and cyberslacking. AL, as a positive leadership style, is proposed as a key factor in mitigating procrastination by fostering a supportive work environment. Specifically, this research examines how AL impacts procrastination through two psychosocial risk factors—lack of supervisor support and lack of workgroup support—which are hypothesized to mediate this relationship. (2) Methods: Data were collected from 738 employees (62.9% women) who completed a survey. Partial least squares structural equation modeling was conducted to explore the direct relationship between AL and procrastination, and indirect relationships through support. (3) Results: The findings indicate that AL
negatively impacts procrastination behaviors, with stronger effects on soldiering compared to cyberslacking. AL is also negatively associated with perceptions of a lack of support from both leaders and workgroups, with a stronger influence on leader support. Both lack of leader and workgroup support significantly predict soldiering but not cyberslacking. (4) Conclusions: This study highlights AL’s potential to mitigate workplace procrastination by reducing perceptions of insufficient support. Organizations should focus on AL training to promote leader authenticity and supportiveness while fostering strong support networks within workgroups to enhance productivity and reduce procrastination behaviors. These findings also contribute to understanding AL’s role in addressing workplace counterproductive behaviors.
... Moreover, in the following sections, we show that affective and cognitive trust present differential patterns of association with other validated constructs, suggesting that keeping the distinction was psychologically meaningful. To evaluate our model, we used five different fit indexes: (a) chi-square test (χ 2 ; [48]), (b) root mean square error of approximation (RMSEA; [49]), (c) comparative fit index (CFI; [50]), (d) Tucker-Lewis index (TLI; [51]) and (e) root mean square and standardized root mean square residual (SRMR; [52]). χ 2 , RMSEA and SRMR are absolute indexes, meaning that they compare the observed model with the theoretical one, without a reference or baseline model [52]. ...
Large Language Models (LLMs) can engage in human-looking conversational exchanges. Although conversations can elicit trust between users and LLMs, scarce empirical research has examined trust formation in human-LLM contexts, beyond LLMs' trustworthiness or human trust in AI in general. Here, we introduce the Trust-In-LLMs Index (TILLMI) as a new framework to measure individuals' trust in LLMs, extending McAllister's cognitive and affective trust dimensions to LLM-human interactions. We developed TILLMI as a psychometric scale, prototyped with a novel protocol we called LLM-simulated validity. The LLM-based scale was then validated in a sample of 1,000 US respondents. Exploratory Factor Analysis identified a two-factor structure. Two items were then removed due to redundancy, yielding a final 6-item scale with a 2-factor structure. Confirmatory Factor Analysis on a separate subsample showed strong model fit (, , , ). Convergent validity analysis revealed that trust in LLMs correlated positively with openness to experience, extraversion, and cognitive flexibility, but negatively with neuroticism. Based on these findings, we interpreted TILLMI's factors as "closeness with LLMs" (affective dimension) and "reliance on LLMs" (cognitive dimension). Younger males exhibited higher closeness with- and reliance on LLMs compared to older women. Individuals with no direct experience with LLMs exhibited lower levels of trust compared to LLMs' users. These findings offer a novel empirical foundation for measuring trust in AI-driven verbal communication, informing responsible design, and fostering balanced human-AI collaboration.
... (Hu & Bentler, 1999), and the root mean square error of approximation (RMSEA) was below .10 (Steiger, 1990). In contrast, results of a one-factor solution indicated a poor fit between the data and the model. ...
The 1992 Task and Ego Orientation in Sport Questionnaire developed by Duda and Nicholls was modified by Walling and Duda in 1995 to assess task and ego orientation in physical education. The modified version was translated into Italian and administered to 1,547 students, 786 girls and 761 boys ages 14 to 19 years, to examine the factor structure. To evaluate the goodness of fit of the expected two-factor solution as in the original questionnaire, confirmatory factor analysis was conducted on four samples of boys and girls of two classes of age (14–16 and 17–19 years). Across sex and age, χ²/df ratios were less than 5.0, fit indices (GFI, NNFI, and CFI) not less than .90, and root mean square error of approximation (RMSEA) below .10. Thus, the two-factor solution of the questionnaire was supported. In the total sample, the two scales showed good internal consistency, with Cronbach α values of .92 for the Ego factor and .83 for the Task factor. The Ego factor accounted for 34.1% of variance and the Task factor accounted for 21.0% of variance.
... GFI ≥ 0.90 = Acceptable fit, GFI ≥ 0.95 = Excellent fit Normed Fit Index (NFI): NFI compares the proposed model to a null model where variables are uncorrelated (Bentler & Bonett, 1980). NFI ≥ 0.90 = Acceptable fit, NFI ≥ 0.95 = Excellent fit Root Mean Square Error of Approximation (RMSEA): RMSEA estimates the model's approximation error per degree of freedom (Steiger, 1990). Lower values indicate a better fit: RMSEA < 0.05 = Good fit, 0.05 ≤ RMSEA ≤ 0.08 = Acceptable fit, and RMSEA > 0.10 = Poor fit. ...
This study offers a comprehensive investigation of mediation analysis in Structural Equation Modelling, highlighting its theoretical basics, statistical practices, and real-world applications. It differentiates mediation from moderation, explaining how mediation helps in understanding indirect relationships between latent variables. Various proposed mediation models, including simple mediation, multiple mediation, and moderated mediation, are discussed in detail. The study also analyses statistical methods such as the Causal Steps Approach (Baron & Kenny, 1986), the Product-of-Coefficients Method (Sobel Test), Bootstrapping, the Bayesian Estimation Method, and Monte Carlo Simulation, each with its respective advantages and limitations. Additionally, advanced Structural Equation Modelling techniques, such as multigroup mediation, longitudinal mediation, and latent variable mediation, are examined to address complex research scenarios. Employing a literature review-based methodology, the study synthesizes existing knowledge on best practices for estimating mediation effects using Structural Equation Modelling. Software tools like AMOS, Mplus, LISREL, and SmartPLS are discussed in the context of model specification, estimation, and evaluation. Real-world applications in business, psychology, human resource management, and marketing are illustrated, including customer trust mediating the relationship between service quality and purchase intention, employee engagement mediating the effect of transformational leadership on job performance, and social media engagement mediating brand trust and purchase intention. Key findings highlight bootstrapping as a better method for estimating indirect effects due to its non-reliance on normality of the data assumptions and Bayesian SEM as a robust substitute for handling small sample sizes and incorporating preceding knowledge. The study also discusses crucial challenges such as measurement error, model misspecification, the need for longitudinal data to establish causal inference, and comparisons between Structural Equation Modelling-based mediation and regression-based mediation using the PROCESS macro. By presenting a structured framework for mediation analysis in Structural Equation Modelling, this current study contributes to advancing causal modelling methods across various disciplines and provides directions for future research.
... Model fit was evaluated using several criteria: the chi-squared to degrees of freedom ratio, which should fall between 1 and 3; the Comparative Fit Index (CFI), which should exceed 0.90 (Bentler, 1990); and the Root Mean Square Error of Approximation (RMSEA) and Standardized Root Mean Square Residual (SRMR), both of which should be less than 0.08 (Steiger, 1990). To compare the models, the Akaike Information Criterion (AIC) was utilized, with lower values indicating better model fit (Burnham & Anderson, 2004). ...
The construction of a fulfilling career and the people management processes within organizations, like the selection of personnel, require a multidisciplinary approach that takes into account psychological, social, and cultural factors. Various concepts have been suggested to explain work motivations and organizational outcomes, including work values. Work values can encompass individual preferences, as well as moral standards and social norms. This broad definition has led to a variety of work value measurement instruments. One brief and cutting-edge measure that integrates different approaches is the New Work Values Scale (NWVS). The aim of this study was to validate the Italian form of this measure (NWVS-I). A sample of 397 Italian adults from 19 to 66 years of age (M = 30.78, SD = 13.38) participated in the study and completed both the New Work Values Scale—Italian form (NWVS-I) and the Portraits Value Questionnaire (PVQ). First, we evaluated the structure of the New Work Values Scale—Italian form (NWVS-I) through confirmatory factor analysis (CFA), followed by a concurrent validity analysis correlating the dimensions of the New Work Values Scale—Italian form (NWVS-I) with those assessed by the Portraits Value Questionnaire (PVQ). We also tested gender invariance. The results confirmed the factor structure of the scale and its validity in the Italian context. The New Work Values Scale—Italian form (NWVS-I) is a useful measure in understanding the work values of individuals in the Italian context. This measure can be used for a wide range of applications, contributing to promoting greater awareness of one’s values and facilitating career choices, personnel selection, and people management aligned with a vision of sustainable organizational development.
... De plus, une analyse factorielle confirmatoire a été effectuée afin de vérifier l'ajustement du modèle à quatre dimensions corrélées aux données. Trois indices sont utilisés pour vérifier l'ajustement du modèle aux données : CFI (Bentler, 1990), NNFI (Tucker et Lewis, 1973) et RMSEA (Steiger, 1990). Un modèle présentant une valeur supérieure à 0,90 pour le CFI et NNFI est jugé adéquat (Schumacker et Lomax, 1996), une valeur supérieure à 0,95 est considérée appréciable. ...
Cette recherche présente la « Resistance To Change Scale » (Oreg, 2003a) et son adaptation en contexte québécois. Cette échelle concerne la disposition à résister au changement, trait reflétant une attitude négative à l’égard de ce dernier. Quatre études ont été réalisées. D’abord, une version préliminaire a été effectuée par la méthode de traduction inversée, et ensuite, elle a été évaluée par des experts et des enseignants. Puis, deux prétests auprès de deux échantillons d’étudiants universitaires ont été effectués. Finalement, l’Échelle de Disposition à Résister Au Changement (ÉDRAC) a été soumise à 294 étudiants de 1er cycle. L’ÉDRAC présente diverses preuves de validité et offre un portrait de la disposition à résister au changement des étudiants. Ses caractéristiques sont discutées.
... This analysis tested the model's theoretical framework by comparing the observed correlations with the proposed measurement model to assess the fit and loadings of the factors (Albright & Park, 2009;Bollen, 1989;Hair et al., 2006;Kline, 2015). Five fit indices were used to evaluate the model: (a) chi-square to degrees of freedom ratio (χ2/df), (b) root mean square error of approximation (RMSEA; Steiger, 1990), (c) standardised root mean square residual (SRMR), (d) comparative fit index (CFI; Bentler, 1990), and (e) Tucker-Lewis index (TLI; Bentler & Bonett, 1980) as shown in Table 2. The χ2 statistic is sensitive to sample size, so the χ2/df ratio was used, with values below 3 indicating acceptable fit (Kline, 2015). ...
Keywords Abstract Technology Acceptance Model; Artificial Intelligence in Education; Meta-analysis; Structural Equation Modelling; Educational Technology. The rapid integration of Artificial Intelligence in Education (AIED) transformed teaching and learning processes. The study employed the Technology Acceptance Model (TAM) to analyse factors influencing the acceptance of AI tools in educational settings. By utilising One-step Meta-analytic Structural Equation Modelling (OSMASEM), findings from 17 empirical studies were synthesised to explore the relationships among TAM constructs-Perceived Ease of Use (PEOU), Perceived Usefulness (PU), Attitude Towards Use (ATU), and Intention to Use (ITU)-in the context of AIED. The analysis revealed significant direct and indirect effects, with PEOU strongly influencing PU and both PEOU and PU positively affecting ATU and ITU. The results highlighted TAM's robustness and applicability in predicting technology acceptance behaviours in education, highlighting the critical roles of usability and perceived benefits in driving AI adoption. The findings provided valuable insights for educators, policymakers, and developers aiming to enhance AI integration in education, emphasising the importance of designing user-friendly and beneficial AI tools to foster positive attitudes and increased usage intentions among educators and students.
... To assess the model's goodness of fit, we used the comparative fit index (CFI) [40], the incremental fit index (IFI) [41], and the root mean square error of approximation (RMSEA) [42]. A good model fit is indicated by CFI and IFI values above 0.90 and RMSEA values of 0.08 or less [43]. ...
Background
Parents can experience much stress from parenting, work, and household responsibilities. Parents’ stress recovery experiences, or their lack thereof, can affect parenting practices and influence children’s behavioral problems, which may thereby lead to difficulties for children later in life. Therefore, the relationships among these three factors deserve consideration. This study tested a model of the mediating role of parenting practices in the relationship between parents’ stress recovery experiences and children’s behavioral problems.
Methods
Parents (N = 1,112) of 14-year-old children in the third year of junior high school in Japan completed a questionnaire, yielding 583 valid responses. To accurately determine the relationship among parents’ stress recovery experiences, parenting practices, and children’s behavioral problems, parents of children diagnosed with developmental disabilities and parents who did not respond to the required items in the questionnaire were excluded from the analysis. As a result, 536 of the 583 (89.0%) parents met the inclusion criteria. We conducted a path analysis, following the hypothesis that parents’ stress recovery experiences, via their parenting practices, are associated with children’s behavioral problems.
Results
The path analysis results indicated that parents’ stress recovery experiences of relaxation and mastery were positively associated with positive nurturing attitudes, whereas mastery and control were negatively associated with negative nurturing attitudes. Furthermore, positive nurturing attitudes were negatively associated with externalizing and internalizing problem behaviors, whereas negative nurturing attitudes were positively associated with externalizing and internalizing problem behaviors. In other words, the hypothesis that parents’ stress recovery experiences of relaxation, mastery, and control reduce children’s behavioral problems via promoting nurturing parental attitudes was supported.
Conclusions
The results indicate that the higher the level of parents’ stress recovery experiences, the lower the level of reported children’s behavioral problems. Parents’ stress recovery experiences correlated with parenting practices, which partially mediated the relationship of the parents’ stress recovery with children’s behavioral problems. The suggestion is that increasing parents’ stress recovery experiences, improving parenting practices and related behaviors, and strengthening the parent–child relationship are important measures that can be mutually beneficial for parents, children, and the overall family relationship.
... Neither covariate was associated with beliefs that firearm ownership nor firearm storage practices was related to suicide risk. approximation (RMSEA) ≤ 0.08 [52] and a Standardized Root Mean Squared Residual (SRMR) ≤ 0.06. ...
Background
Firearms are the primary method by which US military personnel die by suicide, and those at highest risk tend to store firearms unsafely. Promoting secure firearm storage practices is a major component of the Department of Defense’s suicide prevention strategy, but perceptions about firearms being associated with suicide risk may impact such efforts.
Purpose
This study examined perceptions that (1) firearm ownership and (2) storage practices are associated with suicide risk and whether key sociopsychological factors (e.g., entrapment, threat perceptions, honor ideology) were associated with these beliefs in a sample of Active Duty (AD) enlisted Army personnel. We then examined if associations varied as a function of firearm ownership or a lifetime history of suicidal thoughts and/or behaviors (STBs).
Methods
Survey data about sociopsychological factors and ownership-suicide risk beliefs and storage-suicide risk beliefs were collected from 399 AD Army personnel. Multiple regression and multigroup path analyses were used.
Results
Greater intolerance of uncertainty and entrapment, and weaker honor ideology, were associated with greater ownership-suicide risk beliefs, whereas being a parent of a minor child was linked with weaker ownership-suicide risk beliefs. None of the variables examined were associated with storage-suicide risk beliefs. Participants with a lifetime history of STBs who had higher threat perceptions endorsed weaker ownership-suicide risk beliefs.
Conclusions
AD Army personnel may tend to believe that firearm ownership and storage practices are largely unrelated to suicide risk. More tailored messaging and suicide-gun violence prevention efforts are likely needed. Findings have important implications for military suicide prevention efforts.
... These results indicate that Responsiveness, Assurance, Empathy, and Tangibility positively influence IP, while Reliability has no measurable effect. (Kline, 2011;Hu & Bentler, 1999;Steiger, 1990). ...
This study investigates the impact of service quality dimensions on investors' perceptions of DEMAT account services in Nepal. Explanatory research design has been employed with quantitative approach. A structured questionnaire was used to collect primary data among the investors in the Nepal Stock Exchange using convenient sampling method and the constructs were validated for accuracy and reliability. The findings indicate that responsiveness, assurance, empathy, and tangibility significantly influence investor satisfaction and trust, while reliability does not have a notable impact. These results highlight a shift in investor priorities within the digital financial ecosystem. Investors increasingly value quick support, personalized services, and well-designed digital platforms over traditional measures of reliability. This study provides practical recommendations for service providers to enhance customer experiences by focusing on real-time support, fostering trust, and offering user-friendly digital interfaces. By aligning their services with evolving investor expectations, providers can strengthen customer satisfaction and build long-term loyalty in the competitive financial services market. This research contributes to understanding investor behavior and offers insights for improving service quality in digital financial platforms.
... Item analysis and exploratory factor analysis were performed in sample (1) Among them, the items with correlation coefficient less than 0.4 in item analysis was deleted, and the Keiser-Meyer-Olkin (KMO) and Bartlett sphericity test χ 2 were was used to explain the suitability of the scale as an exploratory factor analysis. KMO (greater than 0.7) and P value of Bartlett sphericity test χ (less than 0.05) indicated that the items of the scale were 2 suitable for exploratory factor analysis [26].Confirmatory factor analysis, convergent validity, discriminant validity, internal consistency reliability were tested in sample (2) The indicators in confirmatory factor analysis included: chi-2 square/degree of freedom ratio (χ 2 /df ), comparative fit index (CFI), Tucker-Lewis index (TLI), standardized root mean (standardized root mean) were used in confirmatory factor analysis square residual (SRMR), root mean square root of approximation (RMSEA), wherein, χ 2 /df < 5, CFI > 0.9, TLI > 0.9, SRMR should be close to zero;, RMSEA < 0.08 [27][28][29]. The evaluation criteria of convergent validity and discriminant validity were as follows: the average extracted variance value (AVE) of each factor was greater than 0.5, and the combined reliability was greater than 0.70 as the evaluation criteria of convergent validity. ...
Background
The purpose of this study was to develop a digital self-harm scale suitable for Chinese adolescents, and to test its reliability and validity.
Methods
Through semi-structured interview, literature analysis and expert evaluation, the initial questionnaire was developed, and 1651 students from three middle schools in Jilin Province were selected for questionnaire survey. Item analysis and exploratory factor analysis were carried out, and 843 students were selected for confirmatory factor analysis, convergent validity, discrimination validity, criterion validity, content consistency reliability and retest reliability.
Results
The results showed that the digital self-harm scale consisted of eight items divided into two factors, namely External self image harm and Inner self emotional harm. And 73.47% of the total variance was explained. The two-factor structure model fitted well (²χ/df = 4.2, CFI = 0.994, TLI = 0.989, SRMR = 0.01, RMSEA = 0.062). The total score and each factor score of the digital self-harm scale were negatively correlated with sleep duration, and positively correlated with other criteria. The Cronbach α coefficient of the total scale and each factor was 0.938–0.965, and the retest reliability was 0.983–0.991.
Limitations
The Inner self emotional harm dimension has few questions, the relationship and mechanism between digital self-harm and non-suicidal self-injury is not deep enough.
Conclusions
The digital self-harm scale developed in this study has good validity and reliability, and can be used as a measurement tool to assess the digital self-harm of Chinese adolescents.
... More specifically, to access validity and reliability of the measurement model, we implemented confirmatory factor analysis. To evaluate the model-data fit, the chi-square test (χ2), χ2/df, the Tucker-Lewis Index (TLI), the root-mean-square error of approximation (RMSEA), the comparative fit index (CFI), and the standardized root-mean-residual (SRMR) had been carried out (Weston & Gore, 2006;Hu & Bentler, 1999;Quintana & Maxwell, 1999;Steiger, 1990). Regarding the multilevel model test, we administered several ways to evaluate the hypotheses. ...
Prior scholarly works suggest that workers' promotive behavior and positive perception of decent work enhance performance, and employers prefer and are fair to workers with supportive voice behavior. Nonetheless, Bangladeshi workers tend to display destructive voice behavior, leaving the possibility of exploring the influence of their supportive voice. This study examined the influence of workers' supportive voice on their task performance through the mediation of their perception of decent work and the moderation of distributive justice climate. Data had been collected from 396 working adults in the RMG industry in Bangladesh and analyzed using multilevel path analysis. Based on the social exchange theory, the equity theory, and psychology of working theory, the findings showed a positive relationship between workers' supportive voice and task performance with positive mediation of workers' perception of decent work. Distributive justice climate positively moderates the relationship between workers' supportive voice and workers’ perception of decent work but does not significantly moderate the relationship between workers’ perception of decent work and workers’ task performance. The findings suggest that employers should confirm a fair and just workplace to amplify workers’ supportive behavior, decent work perception, and performance.
... A range of model fit indices and the overall chi-square, which was suggested by Hooper et al. [84], were used to evaluate the study model's goodness-of-fit (GOF) on the provided dataset. The comparative fit index [85], the GOF index, the normed fit index, the root mean square error of approximation [84], the standardized root mean square residual [86], and the p-value significance value were among the metrics used to assess the model's GOF. Table 4 presents the overall GOF metrics for the model. ...
It is commonly assumed that information technology capabilities (ITCs) are instrumental in supply chain viability (SCV), despite negligible empirical evidence. Based on the dynamic resource-based view, this study explores how the SCV competitive advantage is influenced by the heterogeneous resource ITC through the internal operating capability postponement (POST). A quantitative survey was administered to 298 senior managers from retail manufacturing firms, to test hypotheses using hierarchical multiple regression analysis. The SPSS PROCESS Macro was used to determine the mediation and interaction effects of the dual-stage moderated-mediation model, identifying a positive correlation between ITC and POST strategies, highlighting that modern real-time data synchronization and on-demand customization IT systems are needed. POST strategies greatly improve SCV by enhancing operational flexibility, reactivity, and adaptability to dynamic market conditions. The moderators “market orientation” and “demand uncertainty” shape these relationships, emphasizing the need for firms to align their strategies with market dynamics and uncertainties. The research emphasizes the importance of valuable, rare, and inimitable resources in driving sustained competitive advantage. Practical implications suggest strategic investments in advanced IT systems and collaborative efforts in retail manufacturing firms are essential for optimizing supply chain processes. The results, discussion, implications, limitations, and suggestions for additional studies are addressed.
Purpose
This research aims to elucidate the interplay between implementing digital strategies, adopting big data analytics–artificial intelligence (BDAAI), and business process innovation, with a particular emphasis on assessing the moderating impact of digital culture. This article explores how big data analytics can provide organizations with the tools and resources to utilize their data assets effectively, fostering novel and innovative processes.
Design/methodology/approach
The research employed a questionnaire-based approach to collect data from managers in Pakistan’s telecom sector. Data analysis was conducted using SPSS and AMOS software. The measurement model’s suitability was assessed via confirmatory factor analysis (CFA) using AMOS.
Findings
Preliminary results indicate a correlation between these critical factors: digital strategy prioritization, big data analytics incorporation and digital culture cultivation. The study results confirm the effect of digital strategy on business process innovation and support the positive mediating role of the adoption of BDAAI and the moderating role of digital culture.
Research limitations/implications
The research offers insights but is limited to Pakistan’s telecom industry. Digital strategy is crucial for innovation amid digital transformation, with BDAAI enhancing process innovation. The digital culture in telecom will drive industry digitalization through BDAAI in business innovation.
Originality/value
Leveraging artificial intelligence within a digital culture context could be a productive tool for improving business processes. This research represents a novel exploration of the intersection between digital strategy, BDAAI and digital culture within the context of the telecommunications industry.
Purpose
To examine the bidirectional relationships between sleep quality and cognitive function in older Chinese, and further examine the sex differences in the relationships using the random intercept cross-lagged panel model.
Design
A secondary observational analysis of a physical activity clustered randomized controlled trial (The Stay Active While Aging).
Setting
Eight villages in Sichuan, China.
Subjects
A total of 511 adults aged 60 or older. The response rate was 97.3%.
Measures
The Pittsburgh Sleep Quality Index was used to examine sleep quality. Cognitive function was assessed by the Telephone Interview for Cognitive Status.
Results
The mean age was 71.0 (SD, 5.710) years and 227 (44.4%) were men. Sleep quality in the previous wave was associated with cognitive function in the subsequent wave (β = −0.135, [95%CI -0.244 to −0.026], wave 2 to 3; β = −0.108, [95%CI -0.204 to −0.013], wave 4 to 5). Cognitive function in the previous wave was associated with sleep quality in the subsequent wave (β = −0.404, [95%CI -0.566 to −0.242], wave 3 to 4; β = −0.224, [95%CI -0.392 to −0.055], wave 4 to 5). Such relationships were significant only in women.
Conclusions
There were bidirectional relationships between sleep quality and cognitive function in older adults, especially in women. Future cognition interventions may find it helpful to improve sleep quality, and vice versa, particularly in women.
Many dimensions of teacher working conditions influence both teacher and student outcomes; yet, analyses of schools’ overall working conditions are challenged by high correlations among the dimensions. Our study overcame this challenge by applying latent profile analysis to school-level measures of school leadership, instructional agency, professional growth opportunities, rigorous instruction, managing student behavior, family engagement, physical environment, and safety. We identified four classes of schools: Supportive (61%), Unsupportive (7%), Unstructured (22%), and Structured (11%). The patterns of these classes suggest that schools may face tradeoffs between factors such as more teacher autonomy for less instructional rigor or discipline. Teacher satisfaction and their stated career intentions were predicted by their school’s working conditions class, and school contextual factors predicted class membership. By identifying formerly unseen profiles of school-level teacher working conditions and considering the implications of being a teacher in each, decision-makers can provide schools with targeted supports and investments.
Purpose
This study aims to investigate the determinants of Moroccan consumers’ intentions to boycott products associated with Israel amidst the prolonged Palestinian–Israeli conflict. As global interest in ethical consumption and consumer activism intensifies, this research explores how sociopolitical sentiments influence boycott behaviors in emerging markets.
Design/methodology/approach
This study uses a quantitative methodology based on a novel technique that comprised a two-phase analysis including structural equation modeling (SEM) and machine learning through artificial neural network (ANN). SEM was used to analyze direct and indirect relationships among variables, offering insights into both causality and model validity. ANN complemented SEM by examining nonlinear relationships, using multilayer perceptron analysis and cross-validation to assess predictive accuracy and reveal the relative importance of each predictor. An online survey, based on a seven-point Likert scale, gathered data from 234 Moroccan consumers, surpassing the required sample size for robust analysis.
Findings
The results reveal that consumer animosity, positive and negative anticipated emotions, subjective norms and social media influence boycott intentions significantly, whereas negative or positive anticipated emotion do not affect the intention to boycott surrogate Israeli products. This study highlights that consumers’ perceived responsibility and emotional responses to geopolitical issues shape their purchase behaviors, underlining ethical consumption’s complexity in Morocco.
Research limitations/implications
This study primarily examines Arab and Muslim participants, potentially limiting its generalizability. Future research should include non-Muslim and non-Arab individuals who oppose Israel, to strengthen the findings on surrogate product consumption and boycott behavior, enhancing the robustness and broader applicability of the conclusions.
Practical implications
This study offers two key practical implications. First, it provides nongovernmental organizations and advocacy groups with insights on leveraging consumer boycotts as effective tools for promoting ethical and social causes. Second, it highlights how MSMEs can gain a competitive advantage by aligning their branding with cultural and ethical values, fostering consumer loyalty in politically engaged markets.
Originality/value
Positioned at the crossroads of Africa and the Middle East, Morocco is not immune to the conflict’s impact on marketing and consumer behavior. This research offers a novel approach to understanding Moroccan consumers’ intention to boycott Israeli surrogate products. This study contributes to global consumer behavior understanding and highlights sociopolitical implications of the Israeli–Palestinian conflict.
This study investigates the impact of digital brand interaction on brand loyalty in Thailand’s automotive consumers, focusing on the mediating role of customer relationship quality. It hypothesizes that different types of digital brand interaction—information‐based, interaction‐based, and service‐based—have varying effects on brand loyalty and customer relationship quality. The participants were 605 car owners from Bangkok, who responded to a structured questionnaire. Employing structural equation modeling, this research analyzed how these types of digital brand interaction influence brand loyalty through customer relationship quality. The digital brand interaction was categorized into three types: information‐based interaction involving passive content delivery, interaction‐based interaction that facilitate two‐way communication, and service‐based interaction providing customer support and services. The outcome measures focused on the perceived customer relationship quality and brand loyalty as influenced by these types of interaction. The findings revealed that information‐based interaction had a negligible effect on both customer relationship quality and brand loyalty, indicating that mere provision of information is insufficient to foster loyalty. Conversely, interaction‐based interaction significantly enhanced customer relationship quality and, subsequently, brand loyalty. Service‐based interaction also positively impacted these variables but to a lesser extent than interactive methods, underscoring the importance of emotional connections facilitated by digital brand interaction. Conclusively, the study suggests that the effectiveness of digital brand interaction in enhancing brand loyalty significantly relies on their capacity to improve customer relationship quality. These insights are crucial for marketers in the automotive industry aiming at leveraging digital platforms for more effective customer engagement and retention strategies in a competitive market.
This research's focus was to develop and validate "The Early Life Dynamics and Narcissism Scale" (ELDNS). A culturally sensitive therapeutic screening tool, designed to identify impacts of early life dynamics and parenting styles on Narcissistic tendencies in men. The study was done in five phases that included semi structured interviews leading to a preliminary set of 29 items refined by expert evaluation, followed by a pilot study, explanatory factor analysis and psychometric testing of the scale. Factor analysis identified two principal factors: "Childhood familial dynamics and adverse experiences "and "Parental influence and emotional outcomes". The scale exhibited good internal consistency and temporal stability. Moreover, evaluations of convergent and divergent validity demonstrated the scale's precision. This tool would have great clinical implications. More research should be conducted to explore if this scale is applicable in the different cultural settings to enhance the robustness of the scale.
This research aimed to investigate measurement analyses that could promote sustainable financial literacy practices, thereby enhancing financial well-being in a socioeconomic environment. It focused on examining the factors of the Financial Well-Being Index (FWI) model and identifying gaps in financial literacy within the context of a circular economy and climate finance. Confirmatory Factorial Analysis (CFA) and Structural Equation Modeling (SEM) were employed using data collected from 402 families in Kosovo during the years 2022-2023. The analyses revealed interrelationships among financial literacy, financial well-being, and the socioeconomic environment. Strong financial behavior was associated with a reduced need for financial education, while the lack of financial balance hindered resilience and well-being. Savings positively impacted the quality of life and homeownership. Additionally, the need for financial education positively influenced financial attitude, and financial resilience indirectly affected the financial situation. Financial literacy had both direct and indirect effects on the socioeconomic environment through its impact on financial well-being. The study confirmed the significant role of financial literacy in improving financial well-being and the socioeconomic environment. Future research should evaluate the effectiveness of financial education interventions and explore the relationship between financial literacy, climate policy, and income distribution within the framework of the circular economy and climate finance.
This chapter reveals the results of criterion-related validity tests of the Trifactor Model and the Satellite Model, using a well-characterized, multi-modal, and multi-source study of various approaches to assessing adolescent mental health.
This study explores the impact of “Information Technology Implementation” (IT-Impl) on firms' “Operational Performance” (Op-Per) using the Dynamic Resource-Based View (DRBV), proposing a dynamic influence path including the framework of resources-capability-competitive advantage. The direct effects of IT-Impl on Op-Per have been extensively studied, but not the complex instrumental routes and intermediate processes. This study advances a more sophisticated understanding of the dynamic capabilities in converting IT resources into long-term competitive advantage, particularly identifying the serial mediation of the IT-Impl–Op-Per relationship by supply chain integration (SC-Int) and postponement (Post-P). A quantitative research approach was used to gather data from a sample of 298 top-ranking managers from retail manufacturers to test hypotheses using Smart-PLS. The results show that while IT-Impl positively affects Op-Per through the serial mediating roles, “Information Intensity” negatively moderates these relationships. In practice, Op-Per is influenced by a multitude of factors, including supply chain and internal operating capabilities. The study emphasizes the importance of considering SC-Int and Post-P as dynamic capabilities in leveraging IT-Impl for Op-Per. Organizations should strategically align IT investments with advanced supply chain and internal operating capabilities to gain a sustainable competitive advantage. The results, discussion, contributions, limitations, and potential future directions are provided.
The paramount importance of children's social-emotional well-being and social competence in various contexts has been acknowledged in extant research. However, their association among young children in early childhood education and care (ECEC) remains understudied. Additionally, we need more evidence about whether children's socialemotional well-being, broadened with the less empirically studied basic needs fulfilment, in ECEC is associated with their social competence. Thus, the study investigates this association and how the ECEC arrangements moderate the association using survey from the guardians (N = 6,027) of 4-year-old children in Finland. Structural equation modelling showed that children's enjoyment in ECEC was related to their social competence, but not to the fulfilment of children's basic needs. Moreover, no moderation effects of ECEC arrangements were found. This study reveals the importance of prioritizing the advancement of children's social-emotional well-being and a comfortable environment in ECEC for enhancing children's social competence.
A general approach to the analysis of covariance structures is considered, in which the variances and covariances or correlations of the observed variables are directly expressed in terms of the parameters of interest. The statistical problems of identification, estimation and testing of such covariance or correlation structures are discussed.
Several different types of covariance structures are considered as special cases of the general model. These include models for sets of congeneric tests, models for confirmatory and exploratory factor analysis, models for estimation of variance and covariance components, regression models with measurement errors, path analysis models, simplex and circumplex models. Many of the different types of covariance structures are illustrated by means of real data.
Multivariate methods are employed widely in the analysis of experimental data but are poorly understood by those users who are not statisticians. This is because of the wide divergence between the theory and practice of multivariate methods. This book provides concise yet thorough surveys of developments in multivariate statistical analysis and gives statistically sound coverage of the subject. The contributors are all experienced in the theory and practice of multivariate methods and their aim has been to emphasize the major features from the point of view of applicability and to indicate the limitations and conditions of the techniques. Professional statisticians wanting to improve their background in applicable methods, users of high-level statistical methods wanting to improve their background in fundamentals, and graduate students of statistics will all find this volume of value and use.
Let S represent the usual unbiased estimator of a covariance matrix, Σ0, whose elements are functions of a parameter vector . A generalized least squares (G.L.S) estimate, of may be obtained by minimizing where V is some positive definite matrix. Asymptotic properties of the G.L.S. estimators are investigated assuming only that satisfies certain regularity conditions and that the limiting distribution of S is multivariate normal with specified parameters. The estimator of which is obtained by maximizing the Wishart likelihood function (M.W.L. estimator) is shown to be a member of the class of G.L.S. estimators with minimum asymptotic variances. When is linear in a G.L.S. estimator which converges stochastically to the M.W.L. estimator involves far less computation. Methods for calculating estimates of , estimates of the dispersion matrix of , and test statistics, are given for certain linear models.
The purpose of this article is to present a strategy for the evaluation and modification of covariance structure models. The approach makes use of recent developments in estimation under non-standard conditions and unified asymptotic theory related to hypothesis testing. Factors affecting the evaluation and modification of these models are reviewed in terms of nonnormality, missing data, specification error, and sensitivity to large sample size. Alternative model evaluation and specification error search strategies are also reviewed. The approach to covariance structure modeling advocated in this article utilizes the LISREL modification index for assessing statistical power, and the expected parameter change statistic for guiding specification error searches. It is argued that the common approach of utilizing alternative fit indices does not allow the investigator to rule out plausible explanations for model misfit. The approach advocated in this article allows one to determine the extent of sample size sensitivity and the effects of specification error by relying on existing statistical theory underlying covariance structure models.
J. S. Tanaka and G. J. Huba (see record
1986-10882-001) introduced a general fit index for covariance structure models under generalized least squares estimation that in some cases specialized to the fit indices presented by K. G. Jöreskog and D. Sörbom (1981). For a wide class of models, the general form of this fit index can be expressed as a weighted coefficient of determination. This coefficient is given as the ratio of weighted trace functions of predicted and observed covariance matrix elements. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
An analysis of empirical data often leads to a rejection of a hypothesized model, even if the researcher has spent considerable efforts in including all available information in the formulation of the model. Thus, the researcher must reformulate the model in some way, but in most instances there is, at least theoretically, an overwhelming number of possible actions that could be taken. In this paper a modification index will be discussed which should serve as a guide in the search for a better model. In statistical terms, the index measures how much we will be able to reduce the discrepancy between model and data, as defined by a general fit function, when one parameter is added or freed or when one equality constraint is relaxed. The modification index discussed in this paper is an improvement of the one incorporated in the LISREL V computer program in that it takes into account changes in all the parameters of the model when one particular parameter is freed.
Akaike's Information Criterion is systematically dependent on sample size, and therefore cannot be used in practice as a basis for model selection. An alternative measure of goodness-of-fit, based like Akaike's on the noncentrality parameter, appears to be consistent over variations in sample size.
EQS structural equations program manual. Los Angeles: BMDP Software Fit indices, LaGrange multipliers, constraint changes, and incomplete data in structural models
- P M Bentler
Bentler, P. M. (1989). EQS structural equations program manual. Los Angeles: BMDP Software. Bentler, P. M. (1990). Fit indices, LaGrange multipliers, constraint changes, and incomplete data in structural models. Multivariate Behavioral Research, 25, 163-172.
Models for learning data. Paper presented at the Conference on Best Methods for the Analysis of Change, University of Southern California
- M W Browne
- S H C Toit
Browne, M. W., & Du Toit, S. H. C. (1989, October). Models for learning data. Paper presented at the Conference on Best Methods for the Analysis of Change, University of Southern California, Los Angeles.
LISREL VI: Analysis of linear structural relationships by maximum likelihood, instrumental variables, and least squares methods [Computer program]
- K G Joreskog
- D Sorbom
Joreskog, K. G., & Sorbom, D. (1 984). LISREL VI: Analysis of linear structural relationships by maximum likelihood, instrumental variables, and least squares methods [Computer program]. Mooresville, IN: Scientific Software.
Choosing a multivariate model: Noncentrality and goodness of fit A generalsystem forpath analysis with latentvariables. Unpublished masters thesis Model modification
- R P Mcdonald
- H W Marsh
McDonald, R. P., & Marsh, H. W. (in press). Choosing a multivariate model: Noncentrality and goodness of fit. Psychological Bulletin. J. Steiger Mels, G. (1989). A generalsystem forpath analysis with latentvariables. Unpublished masters thesis. University of South Africa, Department of Statistics, Pretoria, South Africa. Sorbom, D. (1989). Model modification. Psychometrika, 54, 371-384.
EZPATH:A supplementarymoduleforSYSTATandSYGRAPH
- J H Steiger
Steiger, J. H. (1989). EZPATH:A supplementarymoduleforSYSTATandSYGRAPH. Evanston. IL: SYSTAT.
Statistically-based tests for the number of common factors. Paper presented at the annual Spring meeting of the Psychometric Society
- J H Steiger
- J C Lind
Steiger, J. H., & Lind, J. C. (1980, May). Statistically-based tests for the number of common factors. Paper presented at the annual Spring meeting of the Psychometric Society, Iowa City, IA.