EVALUATING THE FACTOR STRUCTURE AND MEASUREMENT INVARIANCE OF INSTRUCTIONAL QUALITY IN MATHEMATICS EDUCATION ACROSS COUNTRIES

Author(s):  
Xin Liu ◽  
Kajsa Yang Hansen ◽  
Martin Valcke ◽  
Jan De Neve
2020 ◽  
Vol 36 (5) ◽  
pp. 777-786 ◽  
Author(s):  
Julia Waldeyer ◽  
Jens Fleischer ◽  
Joachim Wirth ◽  
Detlev Leutner

Abstract. There is substantial evidence that students in higher education who have sophisticated resource-management skills are more successful in their studies. Nevertheless, research shows that students are often not adequately prepared to use resource-management strategies effectively. It is thus crucial to screen and identify students who are at risk of poor resource management (and consequently, reduced academic achievement) to provide them with appropriate support. For this purpose, we extend the validation of a situational-judgment-based instrument called Resource-Management Inventory (ReMI), which assesses resource-management competency (including knowledge of resource-management strategies and the self-reported ability to use this knowledge in learning situations). We evaluated the ReMI regarding factor structure, measurement invariance, and its impact on academic achievement in different study domains in a sample of German first-year students ( N = 380). The results confirm the five-factor structure that has been found in a previous study and indicate strong measurement invariance. Furthermore, taking cognitive covariates into account, the results confirm that the ReMI can predict students’ grades incrementally. Finally, a multi-group analysis shows that the findings can be generalized across different study domains. Overall, we provide evidence for a valid and efficient instrument for the assessment of resource-management competency in higher education.


2016 ◽  
Vol 32 (4) ◽  
pp. 265-272 ◽  
Author(s):  
Mohsen Joshanloo ◽  
Ali Bakhshi

Abstract. This study investigated the factor structure and measurement invariance of the Mroczek and Kolarz’s scales of positive and negative affect in Iran (N = 2,391) and the USA (N = 2,154), and across gender groups. The two-factor model of affect was supported across the groups. The results of measurement invariance testing confirmed full metric and partial scalar invariance of the scales across cultural groups, and full metric and full scalar invariance across gender groups. The results of latent mean analysis revealed that Iranians scored lower on positive affect and higher on negative affect than Americans. The analyses also showed that American men scored significantly lower than American women on negative affect. The significance and implications of the results are discussed.


2020 ◽  
Author(s):  
Sean Hallinan ◽  
Melinda Gaddy ◽  
Arpita Ghosh ◽  
Emily Burgen

Vaccines ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 297
Author(s):  
Ya-Chin Yeh ◽  
I-Hua Chen ◽  
Daniel K. Ahorsu ◽  
Nai-Ying Ko ◽  
Kuan-Lin Chen ◽  
...  

The impacts of novel coronavirus disease-2019 (COVID-19) on human life continue to be serious. To control the spread of COVID-19, the production of effective vaccines is likely to be one of the best solutions. However, vaccination hesitancy may decrease individuals’ willingness to get vaccinated. The Drivers of COVID-19 Vaccination Acceptance Scale (DrVac-COVID19S) was recently developed to help healthcare professionals and researchers better understand vaccination acceptance. The present study examined whether DrVac-COVID19S is measurement invariant across different subgroups (Taiwanese vs. mainland Chinese university students; males vs. females; and health-related program majors vs. non-health-related program majors). Taiwanese (n = 761; mean age = 25.51 years; standard deviation (SD) = 6.42; 63.5% females) and mainland Chinese university students (n = 3145; mean age = 20.72 years; SD = 2.06; 50.2% females) were recruited using an online survey between 5 January and 21 February 2021. Factor structure and measurement invariance of the two DrVac-COVID19S scales (nine-item and 12-item) were tested using confirmatory factor analysis (CFA). The findings indicated that the DrVac-COVID19S had a four-factor structure and was measurement invariant across the subgroups. The DrVac-COVID19S’s four-factor structure was supported by the CFA results is a practical and valid instrument to quickly capture university students’ willingness to get COVID-19 vaccination. Moreover, the DrVac-COVID19S can be used to compare university students’ underlying reasons to get COVID-19 vaccination among different subgroups.


2021 ◽  
Vol 10 (13) ◽  
pp. 2850
Author(s):  
Amparo Oliver ◽  
Trinidad Sentandreu-Mañó ◽  
José M. Tomás ◽  
Irene Fernández ◽  
Patricia Sancho

CASP-12 (Control, Autonomy, Self-realization, and Pleasure scale) is one of the most common internationally used measures for quality of life in older adults, although its structure is not clearly established. Current research aims to test the factor structure of the CASP-12, so as to provide evidence on reliability and external validity, and to test for measurement invariance across age groups. Data from 61,355 Europeans (≥60 years old) from the Survey of Health, Ageing and Retirement in Europe wave 7 were used. CASP-12, EURO-D (European depression scale), self-perceived health, and life satisfaction measurements were included. Reliability and validity coefficients, competing confirmatory factor models, and standard measurement invariance routine were estimated. A second-order factor model with the original factor structure was retained. The scale showed adequate reliability coefficients except for the autonomy dimension. The correlation coefficients for external validity were all statistically significant. Finally, CASP-12 is scalar invariant across age. We conclude that the best-fitting factor structure retained allows using CASP-12 either by factors, or as an overall score, depending on the research interests. Findings related to CASP-12 measurement invariance encourage its use in the oldest-old too. When comparing the dimensions across age groups, as people age, autonomy slightly increases and the rest of the dimensions decline.


2020 ◽  
Vol 47 (8) ◽  
pp. 996-1013
Author(s):  
Laura Ros ◽  
Carmen Zabala ◽  
Dulce Romero-Ayuso ◽  
Verónica Jimeno ◽  
Jorge J. Ricarte

Although the Barratt Impulsiveness Scale Version 11 (BIS-11) is one of the most widely used instruments to assess impulsivity, its factor structure remains controversial. Several authors have suggested that cultural factors may have an impact on its factor structure. It is also necessary to study the measurement invariance of the scale in different populations, especially in the case of incarcerated individuals, given their high level of impulsivity. This study had two objectives: (a) to evaluate the factor structure of the BIS-11 and its measurement invariance across community and incarcerated samples and (b) to evaluate the effect of impulsiveness on criminal recidivism. The results revealed a two-factor structure: Motor and Nonplanning Impulsivity. This solution was invariant across groups. In addition, increased Motor Impulsivity was related to higher criminal recidivism through an increase in aggression. These results corroborate the importance of implementing interventions to reduce impulsivity as a means of preventing recidivism.


2020 ◽  
Vol 8 ◽  
Author(s):  
Chung-Ying Lin ◽  
Jung-Der Wang ◽  
Li-Fan Liu

Objectives: To translate and validate a recently developed quality of life instrument (WHOQOL-AGE) on geriatric population into Chinese.Method: Using cross-sectional observational design, the WHOQOL-AGE was conducted among older people through interview. Confirmatory factor analysis (CFA) was used to examine the factor structure and multigroup CFA used to examine the measurement invariance.Results: Through convenience sampling, 522 older adults (mean age = 73.42) participated in the study. Among them, 194 were males, 213 had an educational level at primary school or below, 398 were residing in the community, and 307 were aged 70 years or above. A bifactor structure (items Q1–Q8 are embedded in the factor 1; items Q9–Q13 embedded in the factor 2; and all the items embedded in an additional construct of QoL) was confirmed by the CFA in both the entire sample (χ2 = 25.4; df = 51; p = 0.999) and the subgroup sample with age 70 years or above (χ2 = 25.28; df = 51; p = 1.000). Multigroup CFAs results supported the measurement invariance for the WHOQOL-AGE across genders, having different educational levels, living in different settings and age groups. It also shows good known-groups validity.Conclusions: The promising psychometric properties of the WHOQOL-AGE were found in our convenience sample of older Taiwanese. The supported measurement invariance indicates that the older people in different conditions of gender, educational level, and living setting interpret the WHOQOL-AGE similarly. However, our results should be interpreted with cautious because of the sample representativeness.


Sign in / Sign up

Export Citation Format

Share Document