Regression Analysis of ICT Impact Factors on Early Adolescents’ Reading Proficiency in Five High-Performing Countries

Xiao, Yanyan; Liu, Yang; Hu, Jie

doi:10.3389/fpsyg.2019.01646

Cited by 46 publications

(34 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM is a supervised machine learning approach. It constructs a model dealing with input with different labels and outputting data so that it can predict future situations ( In this model, SVM-recursive feature elimination (SVM-RFE) is an important approach to select features according to their degree of significance to differentiation (Guyon, Weston, Barnhill, & Vapnik, 2002;Jin et al, 2015;Xiao, Liu, & Hu, 2019). The feature with the smallest significance is removed each time.…”

Section: Svm Modellingmentioning

confidence: 99%

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

Dong¹,

Hu²

2019

IJEL

Self Cite

View full text Add to dashboard Cite

This study identified the contextual factors which differentiated 15-year-old students with high- and low-achieving reading literacy in Singapore based on Program for International Student Assessment (PISA) 2015. 4,015 students from Singapore were collected from the public dataset of PISA 2015, with 2,646 high-achieving students and 1,369 low-achieving students in PISA reading literacy test. The impact of the overall 49 contextual factors on reading literacy was analyzed in three levels: student level, family level and school level. Support vector machine (SVM), a machine learning approach, was applied to analyze these contextual features. It indicated that SVM could effectively distinguish these two cohorts of readers with an accuracy score of 0.78. SVM-based recursive feature elimination (SVM-RFE), another machine learning approach, was then applied to rank these selected features. These features were outputted in descending order with regard to the degree of their significance to the differentiation. At last, an optimal set with 15 contextual factors was selected by RFE-CV (cross validation), which collectively affected the differentiation of students with high- and low-level of reading literacy. Based on the analysis, implications to further improving students’ reading literacy can be achieved.

show abstract

Section: Svm Modellingmentioning

confidence: 99%

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

Dong¹,

Hu²

2019

IJEL

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, as shown in all cases, the percentage of variability in academic competencies that is explained by the different specific motor skills varied from R 2 adj = 0.196 to R 2 adj = 0.274. In the humanities and social sciences, these R 2 adj values lie within an acceptable range, with these values being quite typical (and even other lower ones) in many education studies, some of which also focus on the explanation of academic performance (Oliveira et al, 2017;Pires et al, 2017;Cueli et al, 2019;Morales-Rodríguez et al, 2019;Schorr, 2019;Xiao et al, 2019;Tinajero et al, 2020). Social phenomena are complex and multidimensional, so it is not expected that all relevant variables indicating the subject's behavior will be included.…”

Section: Discussionmentioning

confidence: 85%

“…Social phenomena are complex and multidimensional, so it is not expected that all relevant variables indicating the subject's behavior will be included. Therefore, it is very difficult to explain a very large amount of variation (Neter et al, 2012;Xiao et al, 2019). Also, it should be highlighted that even if the R 2 adj values were considered to be low, the low p-values suggest that motor skills included in the models were significantly correlated with academic competencies, meaning that important conclusions could still be drawn from the models (Neter et al, 2012).…”

Section: Discussionmentioning

confidence: 99%

Association Between Preschoolers’ Specific Fine (But Not Gross) Motor Skills and Later Academic Competencies: Educational Implications

2020

View full text Add to dashboard Cite

Motor development is an inseparable component of cognitive development. So, to develop the mind, it is necessary to work the body. Therefore, Early Childhood Education curricula and the scientific literature emphasize the need to promote the development of motor skills during the 1st years of life. These skills are necessary for learning and subsequent academic performance. However, studies frequently offer only a partial view of these relationships. Few works have analyzed the specific relationships between different components of preschool gross and fine motor skills and subsequent performance on different academic competencies. Further, they present discrepant results. The aim of this study was to determinate which specific components of gross and fine motor skills assessed in Spanish students during the final year of Early Childhood Education (5 to 6-year-olds) were associated with different academic competencies assessed in the following academic year, when the students were in their 1st year of Primary Education. The final sample consisted of 38 Spanish students, aged 5. A mixed methods approach was used. It consisted of systematic observation to assess specific components of gross and fine motor skills when children were in the Early Childhood Education period, and selective methodology to evaluate their academic competencies (specifically in literacy and mathematics and overall), 1 year later, once in Primary Education. Multiple linear regression models were constructed using the computing language R to examine the association between motor skills and academic competencies. The results indicated that only the components of fine motor skills showed associations with academic competencies. The pattern of association varied when literacy and mathematics competencies were specifically and individually assessed and when overall academic competency was considered. The two assessed fine motor skills (Coordination and Integration) were associated with literacy competency (β = 0.344, p = 0.025; β = 0.349, p = 0.024, respectively) and overall academic competency (β = 0.267, p = 0.065; β = 0.493, p = 0.001, respectively). However, only

show abstract

“…The percentage of variability in AA that is explained by these 3 variables (EF, PA and gender) varied from R 2 adj = 0.183 to R 2 adj = 0.272, values found to be within an acceptable range in the social sciences, in general, and specifically, in the area of educational research [ 71 , 72 , 73 ]. AA is a multi-dimensional phenomenon and therefore it is impossible to consider all of the relevant and diverse variables participating.…”

Section: Discussionmentioning

confidence: 99%

Academic Achievement in Spanish Secondary School Students: The Inter-Related Role of Executive Functions, Physical Activity and Gender

Pérez

Bestué

2021

IJERPH

View full text Add to dashboard Cite

There is a growing interest in determining which variables contribute to students’ academic performance, since this performance is associated with their wellbeing and with the progress of the nation. This study analyzed whether different variables (executive functions and physical activity levels, gender and academic year) of 177 Spanish Compulsory Secondary School students contributed to their academic performance. The Behavior Rating Inventory of Executive Function 2 (BRIEF-2), Physical Activity Questionnaire for Adolescents (PAQ-A) and an ad hoc questionnaire were used to determine the students’ executive functioning, physical activity level, gender and academic year, respectively. Students’ grades were considered to be indicators of their academic achievement. Seven multiple linear regression models were constructed using the R computing language to examine the association between academic achievement (considered in each of the 5 subjects: Language, Mathematics, Geography and History, English and Physical Education; the mean of the instrumental subjects—Language and Mathematics—and the mean of all the subjects) and the independent variables. The results indicated that executive functions, physical activity and gender contributed to academic performance, but academic year did not. This suggests that students with good executive functions, who perform physical activity and are female, would have better academic achievement. This information should be considered when designing interventions to improve student academic achievement.

show abstract

Regression Analysis of ICT Impact Factors on Early Adolescents’ Reading Proficiency in Five High-Performing Countries

Cited by 46 publications

References 64 publications

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

Association Between Preschoolers’ Specific Fine (But Not Gross) Motor Skills and Later Academic Competencies: Educational Implications

Academic Achievement in Spanish Secondary School Students: The Inter-Related Role of Executive Functions, Physical Activity and Gender

Contact Info

Product

Resources

About