Identification of Factors Associated With School Effectiveness With Data Mining Techniques: Testing a New Approach

Abstract

The study of school effectiveness and the identification of factors associated with it are growing fields of research in the education sciences. Moreover, from the perspective of data mining, great progress has been made in the development of algorithms for the modeling and identification of non-trivial information from massive databases. This work, which falls within this context, proposes an innovative approach for the identification and characterization of educational and organizational factors associated with high school effectiveness. Under a perspective of basic research, our aim is to study the suitability of decision trees, techniques inherent to data mining, to establish predictive models for school effectiveness. Based on the available Spanish sample of the PISA 2015 assessment, an indicator of the school effectiveness was obtained from the application of multilevel models with predictor variables of a contextual nature. After selecting high- and low-effectiveness schools in this first phase, the second phase of the study was carried out and consisted of the application of decision trees to identify school, teacher, and student factors associated with high and low effectiveness. The C4.5 algorithm was calculated and, as a result, we obtained 120 different decision trees based on five determining factors (database used; stratification in the initial selection of schools; significance of the predictor variables of the models; use of items and/or scales; and use of the training or validated samples). The results show that the use of this kind of technique could be appropriate if mainly used with correctly pre-processed data that include the combined information available from all educational agents. This study represents a major breakthrough in the study of the factors associated with school effectiveness from a quantitative approach, since it proposes and provides a simple and appropriate procedure for modeling and establishing patterns. In doing so, it contributes to the development of knowledge in the field of school effectiveness that can help in educational decision-making.

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

“…It is important to note that we have aggregated student variables to the school database to build the decision tree. In this sense, previous research shows better model fits in decision trees computed with aggregated data in the school level compared to the use of student level as the unit of analysis (Martínez-Abad, 2019).…”

“…The study proposes a systematic process for high and low performing schools through the use of clustering techniques, followed by a predictive approach that yielded results with no interference from previous theoretical models, allowing for the emergence of relationships that might be overlooked or less researched in traditional multivariate literature. In this sense, taking into account the main advantages of Data Mining Techniques (Witten et al, 2016;Martínez-Abad, 2019), it was possible to obtain an explanatory model of school performance based on decision trees with acceptable levels of fit. In contrast to the usual practice in EDM research with large scale assessments (Liu and Whitford, 2011;Oskouei and Askari, 2014;Costa et al, 2017;Kılıç Depren et al, 2017;Asensio-Muñoz et al, 2018;Tourón et al, 2018), and according to current studies (She et al, 2019;Martínez-Abad et al, 2020), we limited the size of the final decision tree.…”

“…The past decade has seen the publication of many research works that use EDM techniques for performance prediction. Although there is some diversity in terms of the particular techniques used, the most popular seem to be decision trees and their different algorithms, such as Classification and Regression Trees (CART) (Asensio-Muñoz et al, 2018;Gabriel et al, 2018;She et al, 2019), Chi-squared Automatic Interaction Detection (CHAID) (Aksu and Güzeller, 2016;Asensio-Muñoz et al, 2018;Tourón et al, 2018) or other algorithms like C4.5 (Liu and Ruiz, 2008;Oskouei and Askari, 2014;Martínez-Abad, 2019) or J48, which is another form of the C4.5 algorithm (Aksu and Güzeller, 2016;Martínez-Abad and Chaparro-Caso-López, 2016;Kılıç Depren et al, 2017;Martínez-Abad et al, 2020). Some of these studies aggregate student variables to school level (e.g., Martínez-Abad, 2019), however, there are not, to our knowledge, any basic studies on the effects of the aggregation bias on the computation of data mining models.…”

“…Additionally, thanks to the emergence of big data, new possibilities in the statistical analysis of all types of databases have appeared in recent years. Namely, data mining has appeared in the past few years as one of the emerging techniques to analyse PISA data (Liu and Whitford, 2011;Tourón et al, 2018;Martínez-Abad, 2019;She et al, 2019), although it is a less-explored analysis method.…”

Towards Mining Creative Thinking Patterns from Educational Data

“…It places a strong emphasis on training and its numerous ramifications. It also establishes a rating system that monitors how websites are used in order to enhance the educational system 117,130 ; and (iv) Merging pedagogy with big data: Incorporating big data concepts into various courses and emphasizing their educational implications 52,73 .…”