Previous studies on academic performance
| References | Methods | Findings |
|---|---|---|
| Hoxby (2000) | Regression models | There is no significant impact of class size on student achievement |
| Fan and Chen (2001) | General linear model | A positive link between parental involvement and student achievement |
| Barnett et al. (2002) | Linear programming techniques | A positive association between larger secondary school size and effectiveness, even when considering cost constraints. This suggests larger schools might outperform smaller ones in terms of academic performance |
| Rivkin et al. (2005) | Regression models | The study found teacher quality, not class size, has the biggest impact on student achievement, with good teachers benefitting all students |
| Archibald (2006) | Hierarchical linear models | The study suggests that expenditures on instruction and instructional support have a positive impact on students’ achievement |
| Lee and Bowen (2006) | Hierarchical linear model | Parent involvement benefits student achievement more for dominant cultural backgrounds |
| Marks et al. (2006) | Item response theory; regressions models | Cultural capital plays a key role in influencing students’ educational outcomes |
| Codjoe (2007) | Interviews | Supportive home environment and parental encouragement were significant factors contributing to the academic performance |
| Lei and Zhao (2007) | Hierarchical linear models; ANOVA tests | Quantity of technology use alone does not impact achievement, but focused and quality uses were linked to higher academic achievements |
| Steinmayr and Spinath (2008) | Regression models | Personality traits and achievement motivation did not explain gender differences in German school marks |
| Caro et al. (2009) | Hierarchical linear models; panel data models | Socioeconomic background has a significant impact on students achievement |
| Mensah and Kiernan (2010) | Tobit regression models; univariate and multivariate analyses | The study found that boys from families with less educated mothers achieved lower educational outcome compared to girls in similar situations |
| Hartas (2011) | Univariate analyses of variance; chi-square tests | Socioeconomic factors have a stronger influence on children’s language and literacy development than on their socio-emotional competence |
| S. Huang and Fang (2013) | Regression model, artificial neural networks, radial basis function and support vector machines | Past academic performance is the best predictor of students achievement |
| Wally-Dima and Mbekomize (2013) | Descriptive statistics T-tests | The study link female students’ stronger work ethic to their outperformance in accounting compared to males |
| Bosworth (2014) | Regression models | The study found that smaller classes have a smaller achievement gap |
| Hodis et al. (2015) | Hierarchical linear models | Secondary school students with both high aspirations and a focus on meeting minimum requirements achieve better academically |
| Lee and Mallik (2015) | Ordinary least squares | Higher entrance scores, age and grades in specific core subjects positively impact academic achievement in online undergraduates programs |
| Migu_eis et al. (2018) | Random forests, decision trees, support vector machines and naïve bayes | A two part data mining model precisely predicted average grades and graduation time, enabling early intervention to improve student success |
| Ya_gci and Çevik (2019) | Artificial neural networks | Artificial neural networks effectively predicted science course performance for vocational high schools students in Turkey and Malaysia |
| Cruz-Jesus et al. (2020) | Regression models, artificial neural networks, decision trees, extremely randomized trees, random Forest, Support vector machines, K-Nearest Neighbors | AI techniques predicted high school achievement in Portugal |
| Jiao et al. (2022) | Genetic programming | In an online engineering course, the study identified participation, knowledge gain and past performance as key predictors of student achievement using AI |
| García-Martínez et al. (2023) | Systematic review and meta analysis | AI and computational sciences positevly impact student performance and motivation, especially in STEM fields |
| References | Methods | Findings |
|---|---|---|
| Regression models | There is no significant impact of class size on student achievement | |
| General linear model | A positive link between parental involvement and student achievement | |
| Linear programming techniques | A positive association between larger secondary school size and effectiveness, even when considering cost constraints. This suggests larger schools might outperform smaller ones in terms of academic performance | |
| Regression models | The study found teacher quality, not class size, has the biggest impact on student achievement, with good teachers benefitting all students | |
| Hierarchical linear models | The study suggests that expenditures on instruction and instructional support have a positive impact on students’ achievement | |
| Hierarchical linear model | Parent involvement benefits student achievement more for dominant cultural backgrounds | |
| Item response theory; regressions models | Cultural capital plays a key role in influencing students’ educational outcomes | |
| Interviews | Supportive home environment and parental encouragement were significant factors contributing to the academic performance | |
| Hierarchical linear models; ANOVA tests | Quantity of technology use alone does not impact achievement, but focused and quality uses were linked to higher academic achievements | |
| Regression models | Personality traits and achievement motivation did not explain gender differences in German school marks | |
| Hierarchical linear models; panel data models | Socioeconomic background has a significant impact on students achievement | |
| Tobit regression models; univariate and multivariate analyses | The study found that boys from families with less educated mothers achieved lower educational outcome compared to girls in similar situations | |
| Univariate analyses of variance; chi-square tests | Socioeconomic factors have a stronger influence on children’s language and literacy development than on their socio-emotional competence | |
| Regression model, artificial neural networks, radial basis function and support vector machines | Past academic performance is the best predictor of students achievement | |
| Descriptive statistics T-tests | The study link female students’ stronger work ethic to their outperformance in accounting compared to males | |
| Regression models | The study found that smaller classes have a smaller achievement gap | |
| Hierarchical linear models | Secondary school students with both high aspirations and a focus on meeting minimum requirements achieve better academically | |
| Ordinary least squares | Higher entrance scores, age and grades in specific core subjects positively impact academic achievement in online undergraduates programs | |
| Random forests, decision trees, support vector machines and naïve bayes | A two part data mining model precisely predicted average grades and graduation time, enabling early intervention to improve student success | |
| Artificial neural networks | Artificial neural networks effectively predicted science course performance for vocational high schools students in Turkey and Malaysia | |
| Regression models, artificial neural networks, decision trees, extremely randomized trees, random Forest, Support vector machines, K-Nearest Neighbors | AI techniques predicted high school achievement in Portugal | |
| Genetic programming | In an online engineering course, the study identified participation, knowledge gain and past performance as key predictors of student achievement using AI | |
| Systematic review and meta analysis | AI and computational sciences positevly impact student performance and motivation, especially in STEM fields |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.