Results of a comprehensive simulation study are reported investigating the effects of sample size, test length, number of attributes and base rate of mastery on item parameter recovery and ...classification accuracy of four DCMs (i.e., C-RUM, DINA, DINO, and LCDMREDUCED). Effects were evaluated using bias and RMSE computed between true (i.e., generating) parameters and estimated parameters. Effects of simulated factors on attribute assignment were also evaluated using the percentage of classification accuracy. More precise estimates of item parameters were obtained with larger sample size and longer test length. Recovery of item parameters decreased as the number of attributes increased from three to five but base rate of mastery had a varying effect on the item recovery. Item parameter and classification accuracy were higher for DINA and DINO models.
This article provides a review of software packages for fitting maximum likelihood estimation of the deterministic input, noisy “and” gate (DINA) model. Six software packages—flexMIRT, Latent GOLD, ...mdltm, Mplus, OxEdit, and R—are considered. Each package is reviewed regarding data manipulation, statistical capabilities, output, and documentation. The results of these packages are compared using a sample data set and a Q-matrix. The article aims to give the reader a summary of the different capabilities of each package.
Full text
Available for:
NUK, OILJ, SAZU, UKNU, UL, UM, UPUK
Whether gamification is an organized structure that contributes to student achievement, a simple pontification process or total nonsense is a matter of debate. In such, this study was conducted to ...provide a scientific answer while exhibiting the gamification effect on student achievement with the meta-analysis method, which is based on experimental research that investigates the effect of gamification on student achievement between 2010 and 2016. As a result of the completed meta-analysis, a common effect size value that was estimated by compiling experimental studies was found to be 0.557. This value shows that gamification has a moderately positive (Cohen, 1988) effect on student achievement. It is exhibited that there is no publication bias regarding determining the effect's validity. Calculated 0.557 Hedges' g value's omega square equivalent is .072. This value shows that gamification has added 7.2% positive value to academic achievement according to 45 experimental results involving 3,487 students from different countries.
Full text
Available for:
BFBNIB, NUK, PILJ, SAZU, UL, UM, UPUK
The purpose of this study was to estimate the overall reliability values for the scores produced by Runco Ideational Behavior Scale (RIBS) and explore the variability of RIBS score reliability across ...studies. To achieve this, a reliability generalization meta-analysis was carried out using the 86 Cronbach's alpha estimates obtained from 77 studies that met the inclusion criteria. The analyses were conducted with the random-effects model using the transformed coefficient values from the Bonett's method. The average transformed coefficient alpha value was estimated to be .898 (95% CI: .887, .907) and found to be significant (p < .001) under the random-effects model. Analog to the ANOVA and meta-regression analyses were also conducted using the sample descriptors to explore the variability of the Cronbach's alpha estimates. Results revealed that education level (university vs non-university) and test version (19-item vs 23-item) significantly affected reliability estimates, suggesting that the alphas differed across the subcategories. The average reliability estimates for non-university samples (α = .925) and 23-item version (α = .913) were found to be higher than university samples (α = .886) and 19-item version (α = .865). Results also indicated that higher number of items, mean, and standard deviation of total scale score were associated with increased internal consistency in the RIBS. Suggestions are proposed for substantive research using the RIBS and for future psychometric research on the instrument.
Full text
Available for:
BFBNIB, DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
The standard item response theory (IRT) model assumption of a single homogenous population may be violated in real data. Mixture extensions of IRT models have been proposed to account for latent ...heterogeneous populations, but these models are not designed to handle multilevel data structures. Ignoring the multilevel structure is problematic as it results in lower-level units aggregated with higher-level units and yields less accurate results, because of dependencies in the data. Multilevel data structures cause such dependencies between levels but can be modeled in a straightforward way in multilevel mixture IRT models. An important step in the use of multilevel mixture IRT models is the fit of the model to the data. This fit is often determined based on relative fit indices. Previous research on mixture IRT models has shown that performances of these indices and classification accuracy of these models can be affected by several factors including percentage of class-variant items, number of items, magnitude and size of clusters, and mixing proportions of latent classes. As yet, no studies appear to have been reported examining these issues for multilevel extensions of mixture IRT models. The current study aims to investigate the effects of several features of the data on the accuracy of model selection and parameter recovery. Results are reported on a simulation study designed to examine the following features of the data: percentages of class-variant items (30, 60, and 90%), numbers of latent classes in the data (with from 1 to 3 latent classes at level 1 and 1 and 2 latent classes at level 2), numbers of items (10, 30, and 50), numbers of clusters (50 and 100), cluster size (10 and 50), and mixing proportions equal (0.5 and 0.5) vs. non-equal (0.25 and 0.75). Simulation results indicated that multilevel mixture IRT models resulted in less accurate estimates when the number of clusters and the cluster size were small. In addition, mean Root mean square error (RMSE) values increased as the percentage of class-variant items increased and parameters were recovered more accurately under the 30% class-variant item conditions. Mixing proportion type (i.e., equal vs. unequal latent class sizes) and numbers of items (10, 30, and 50), however, did not show any clear pattern. Sample size dependent fit indices BIC, CAIC, and SABIC performed poorly for the smaller level-1 sample size. For the remaining conditions, the SABIC index performed better than other fit indices.
•Evidence from the interventions for parents of children with developmental disabilities (DD) in Türkiye makes it essential to provide a synthesis of the efficacy of relevant interventions. ...Therefore, the main purpose of this meta-analysis is to address the efficacy of interventions for parents of children with DD in Türkiye.•The findinds of the study revealed that the interventions designed for parents of children with DD result in an increase in positive functioning and a reduction in symptoms of mental health conditions in favor of experimental group.•Moderator analyses showed that the study design was a statistically significant moderator of positive functioning. However, other moderators (the gender of the participants, publication type, the type of intervention, the disability type of children, the sample size, and the number of sessions) were not statistically significant for symptoms of mental health conditions and positive functioning.
Previous studies have revealed that parents of children with developmental disabilities (DD) experience various mental health problems. The number of intervention studies has increased for parents of children with DD to reduce symptoms of mental health conditions and increase positive functioning in recent years in Türkiye. The main purpose of this systematic and meta-analytical review is to address the efficacy of interventions for parents of children with DD on symptoms of mental health conditions and positive functioning in Türkiye. The second purpose of this study is to examine the effect of the potential moderators on the efficacy of the interventions in symptoms of mental health conditions and positive functioning. For these purposes, studies published between 2000 and October 2022 were searched in various databases. As a result of the literature search, 61 studies met the inclusion criteria, and 23 studies with 17 independent effect sizes for symptoms of mental health conditions and 12 independent effect sizes for positive functioning were included in the current study. Cohen’s d effect size index was used to calculate the efficacy of intervention studies included in the meta-analysis on symptoms of mental health conditions and positive functioning. Results revealed that the overall mean effect size for the 17 mental health studies was −1.15 and for the 12 positive functioning studies was 2.03 in favor of experimental group. Moderator analyses showed that the study design (experimental vs. quasi-experimental) was a statistically significant moderator of positive functioning. The average effect size for experimental studies was higher than that of quasi-experimental studies. However, other moderators (the gender of the participants, publication type, the type of intervention, the disability type of children, the sample size, and the number of sessions) were not statistically significant for symptoms of mental health conditions and positive functioning. Although the current study has some limitations, the findings revealed that the interventions designed for parents of children with DD result in an increase in positive functioning and a reduction in symptoms of mental health conditions in favor of experimental group.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Studies conducted during the pandemic revealed strong associations between gender and COVID-19 related fear and anxiety. Females perceive coronavirus as a greater threat to personal health and ...population than males. The aim of the current meta-analysis is to estimate gender difference in COVID-19 related fear and anxiety. The second purpose of this study is to clarify the role of potential moderators in COVID-19 fear and anxiety. For these reasons, studies published between March 2020 and October 2021 were searched in various databases (Web of Science, SCOPUS, PubMed, and Google Scholar). In total, 315 studies met the inclusion criteria, and 60 studies for COVID-19 related fear and 23 studies for COVID-19 related anxiety were included in the current study. Cohen's d effect size values were calculated based on these individual studies showing the difference between males and females in terms of COVID-19 related fear and anxiety. Results revealed that gender has a moderate and statistically significant effect on COVID-19 related fear (ES = 0.307) and anxiety (ES = 0.316) in favor of females. Moderator analyses showed that continent variable was a statistically significant moderator of gender difference in COVID-19 related fear and anxiety. The highest effect size of gender differences in COVID-related fear and anxiety were obtained from the studies conducted in Europe. However, other moderators (the average age of sample, culture, timing, and population) were not statistically significant. Although this meta-analysis has a few limitations, the findings showed that COVID-19 outbreak negatively affected females more.
•Gender has a moderate and significant effect on COVID-19 related fear (ES = 0.307) and anxiety (ES = 0.316) in favor of females.•The highest effect size of gender differences in COVID-related fear and anxiety was obtained from the studies conducted in Europe.•Other moderators (the average age of sample, culture, timing, and population) were not statistically significant.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Large-scale assessments are generally designed for summative purposes to compare achievement among participating countries. However, these nondiagnostic assessments have also been adapted in the ...context of cognitive diagnostic assessment for diagnostic purposes. Following the large amount of investments in these assessments, it would be cost-effective to draw finer-grained inferences about the attribute mastery. Nonetheless, the correctness of attribute specifications in the Q-matrix has not been verified, despite being designed by domain experts. Furthermore, the underlying process of TIMSS (Trends in International Mathematics and Science Study) assessment is unknown as it was not developed for diagnostic purposes. Thus, this study suggests an initial validating attribute specifications in the Q-matrix and thereafter defining specific reduced or saturated models for each item. In doing so, the two analyses were validated across 20 countries that were selected randomly for TIMSS 2011 data. Results show that attribute specifications can differ from expert opinions and the underlying model for each item can vary.
This study aimed to adapt the COVID-19 Stress Scales (CSS) into Turkish and provide evidence for construct validity. For this purpose, firstly, Confirmatory factor analysis (CFA) was applied for the ...5-factor model obtained during the development of CSS and the theoretically expected 6-factor model with total of 546 respondents. The findings revealed that the 6-factor model of CSS had a better fit in the Turkish sample. Factor loadings varied between .62 - .95 and correlations between subscales were between .44 - .76. Cronbach's Alpha and McDonald’s ω coefficients for each subscale indicated good-to-excellent internal consistency. To evaluate the criterion-related validity, the Turkish version of The Fear of COVID-19 Scale (FCV-19S) was administered to the participants and the correlation coefficients between this scale and the six subscale of CSS were calculated. We also conducted the Rasch analysis with related items to provide psychometric evidence for their unidimensional structure of each of the six subscales. Lastly, Differential item functioning (DIF) analysis was performed across subgroups by gender, having COVID-19, and being a student. Overall, the results of both CFA and Rasch analyses provided evidence to support the substantive aspect of validity and the appropriateness of the CSS as a measure of COVID-19 stress level in a Turkish sample.
This study aimed to adapt the COVID-19 Stress Scales (CSS) into Turkish and provide evidence for construct validity. For this purpose, firstly, Confirmatory factor analysis (CFA) was applied for the 5-factor model obtained during the development of CSS and the theoretically expected 6-factor model with total of 546 respondents. The findings revealed that the 6-factor model of CSS had a better fit in the Turkish sample. Factor loadings varied between .62 - .95 and correlations between subscales were between .44 - .76. Cronbach's Alpha and McDonald’s ω coefficients for each subscale indicated good-to-excellent internal consistency. To evaluate the criterion-related validity, the Turkish version of The Fear of COVID-19 Scale (FCV-19S) was administered to the participants and the correlation coefficients between this scale and the six subscale of CSS were calculated. We also conducted the Rasch analysis with related items to provide psychometric evidence for their unidimensional structure of each of the six subscales. Lastly, Differential item functioning (DIF) analysis was performed across subgroups by gender, having COVID-19, and being a student. Overall, the results of both CFA and Rasch analyses provided evidence to support the substantive aspect of validity and the appropriateness of the CSS as a measure of COVID-19 stress level in a Turkish sample.