Search

In light of the emergence of statistical analysis techniques based on data mining in education sciences, and the potential they offer to detect non-trivial information in large databases, this paper presents a procedure used to detect factors linked to academic achievement in large-scale assessments. The study is based on a non-experimental, cross-sectional design and a sample of 18,935 high school students from 99 educational institutions in Baja California state (Mexico). The information was collected from ENLACE tests and context surveys given to students in Baja California. Decision trees were used to apply classification techniques, and the results indicate that personal factors are most indicative of academic performance, followed by school-related and social factors. In conclusion, the paper discusses the similarities between the results obtained and those shown in literature, highlighting how simple decision trees allow a greater explanation and interpretation than other models and techniques.

In light of the emergence of statistical analysis techniques based on data mining in education sciences, and the potential they offer to detect non-trivial information in large databases, this paper presents a procedure used to detect factors linked to academic achievement in large-scale assessments. The study is based on a non-experimental, cross-sectional design and a sample of 18,935 high school students from 99 educational institutions in Baja California state (Mexico). The information was collected from ENLACE tests and context surveys given to students in Baja Caclifornia. Decision trees were used to apply classification techniques, and the results indicate that personal factors are most indicative of academic performance, followed by school-related and social factors. In conclusion, the paper discusses the similarities between the results obtained and those shown in literature, highlighting how simple decision trees allow a greater explanation and interpretation than other models and techniques. [ABSTRACT FROM PUBLISHER]

• Decision trees enable the detection of factors that predict school effectiveness. • The predictive model is more accurate for low effectiveness schools. • A single negative factor at school escalates the risk of low effectiveness. With the main goal of identifying the process factors associated with school effectiveness in secondary education, this work presents an innovative methodological proposal. Based on secondary data from the Spanish sample of PISA 2015, high- and low-effectiveness schools were selected by analysing the residuals of the school level (level 2) in multilevel models. Subsequently, decision trees were used to identify the process variables with a greater predictive power for the identification of high- and low-effectiveness schools. While the hierarchical linear models obtained show inter-school variance scores greater than 10%, decision trees achieve a precision greater than 90%. We conclude by analysing the suitability of using decision trees in data originating from large-scale assessments, and examining the obtained factors associated with school effectiveness. [ABSTRACT FROM AUTHOR]