An Exploration of Factors Linked to Academic Performance in PISA 2018 Through Data Mining Techniques

Abstract

International large-scale assessments, such as PISA, provide structured and static data. However, due to its extensive databases, several researchers place it as a reference in Big Data in Education. With the goal of exploring which factors at country, school and student level have a higher relevance in predicting student performance, this paper proposes an Educational Data Mining approach to detect and analyze factors linked to academic performance. To this end, we conducted a secondary data analysis and built decision trees (C4.5 algorithm) to obtain a predictive model of school performance. Specifically, we selected as predictor variables a set of socioeconomic, process and outcome variables from PISA 2018 and other sources (World Bank, 2020). Since the unit of analysis were schools from all the countries included in PISA 2018 (n = 21,903), student and teacher predictor variables were imputed to the school database. Based on the available student performance scores in Reading, Math, and Science, we applied k-means clustering to obtain a categorized (three categories) target variable of global school performance. Results show the existence of two main branches in the decision tree, split according to the schools’ mean socioeconomic status (SES). While performance in high-SES schools is influenced by educational factors such as metacognitive strategies or achievement motivation, performance in low-SES schools is affected in greater measure by country-level socioeconomic indicators such as GDP, and individual educational indicators are relegated to a secondary level. Since these evidences are in line and delve into previous research, this work concludes by analyzing its potential contribution to support the decision making processes regarding educational policies.

Fully Gibbs Sampling Algorithms for Bayesian Variable Selection in Latent Regression Models

“…Home possession (HOMEPOS) and learning time in mathematics (MMINS) were two covariates selected by all approaches, indicating that the social-economic status (SES) of students and learning time in math had an important impact on the improvement of mathematics capacities. These results are consistent with prior literature (e.g., Gamazo & Martínez-Abad, 2020;Kalaycıoğlu, 2015;Lee & Stankov, 2018).…”

The influence of achievement motivation on college students’ employability: A chain mediation analysis of self-efficacy and academic performance

“…Many researchers have found that students’ achievement motivation is closely and positively correlated with academic performance ( She et al, 2019 ; Gamazo and Martínez-Abad, 2020 ). Various constructs of motivation such as perceived control, values, and self-perception can be used as a supplement to intelligence tests to positively predict the academic performance ( Daniels and Dueck, 2022 ).…”

Heritage Outreach, Fossils, Dinosaurs and Sites: How Locals’ Perception Changes After 10 Years of Actions in Historic Urban Villages (Cuenca, Spain)

“…The negative results of teenagers (< 18) were in concordance with the low scores in science obtained by Spanish students, significantly below the 2019 OECD average (Ministry of Education and Professional Training 2019) (see Online Resource 1). It has been addressed that these low academic results were highly related to the national socioeconomic circumstances of the time (Gamazo and Martínez-Abad 2020), which worsened during the 2008 crisis and its subsequent austerity policies (compare in Fig. 1c the National and Castilla-La Mancha expenditure diagrams, also see The Local 2019).…”