Combining statistical and machine learning methods to explore German students’ attitudes towards ICT in PISA

Abstract

In our age of big data and growing computational power, versatility in data analysis is important. This study presents a flexible way to combine statistics and machine learning for data analysis of a large-scale educational survey. The authors used statistical and machine learning methods to explore German students' attitudes towards information and communication technology (ICT) in relation to mathematical and scientific literacy measured by the Programme for International Student Assessment (PISA) in 2015 and 2018. Implementations of the random forest (RF) algorithm were applied to impute missing data and to predict students' proficiency levels in mathematics and science. Hierarchical linear models (HLM) were built to explore relationships between attitudes towards ICT and mathematical and scientific literacy with the focus on the nested structure of the data. ICT autonomy was an important variable in RF models, and associations between this attitude and literacy scores in HLM were significant and positive, while for other ICT attitudes the associations were negative (ICT in social interaction) or non-significant (ICT competence and ICT interest). The need for further research on ICT autonomy is discussed, and benefits of combining statistical and machine learning approaches are outlined.

ICT Motivation in Sixth-Grade Students in Pandemic Times—The Influence of Gender and Age

“…Starting with the analysis of the results obtained, it was generally observed that the assessment of ICT use and engagement in the educational environment was medium-high. This is in line with other studies [5,[45][46][47][48][49][50]. It is true that certain aspects were below the overall average, as in the case where students forget about time when using electronic devices or where they exchange solutions to problems with digital devices using the Internet.…”

“…The main research on the motivation generated by ICT in adolescents is related to education, especially in how the use of ICT in students, at home and at school, influences the performance of reading comprehension [5,45,46], mathematics [47,48] and science [47][48][49][50]. In these three domains or areas of knowledge, there are differences in academic performance.…”

“…However, their appropriate use in schools has highly positive effects [40,43]. Thus, school autonomy over ICT in countries such as Singapore and Turkey before the pandemic had a positive relationship with achievements in science and mathematics [47,50].…”

Análisis sobre el uso de la tecnología en el proceso educativo de la Psicología durante la pandemia Covid-19 considerando la ciencia de datos

“…La ciencia de datos permite identificar, clasificar y evaluar los datos de las variables con el propósito de descubrir información relevante de los fenómenos (Chadaga et al, 2021;Lezhnina & Kismihok, 2021). En el aprendizaje automático, las técnicas sobre la regresión lineal y el árbol de decisión facilitan el análisis sobre las variables independientes y dependientes para establecer las condiciones y relaciones de los eventos predictivos y descriptivos (Lezhnina & Kismihok, 2021).…”

“…De acuerdo con Chadaga et al (2021), la técnica de regresión lineal tienen un papel fundamental en el campo de la medicina debido a que ésta permite analizar y predecir el comportamiento de las enfermedades y virus como el SARS-CoV-2. Incluso, esta técnica de la ciencia de datos permite conocer el nivel de influencia entre las variables de estudio por medio de la división de la muestra en la sección de entrenamiento y evaluación (Chadaga et al, 2021;Lezhnina & Kismihok, 2021;Salas-Rueda, 2021).…”