Conference Agenda

Large-scale assessments provide comprehensive data on the effectiveness of educational policies, allowing countries to evaluate the current state of their education systems. Fundamental elements such as the impact of instructional methods on students, learning barriers, and the contribution of curricula to student achievement are systematically examined through these measurement tools (Erkuş, 2012). In this context, the Programme for International Student Assessment (PISA) conducted by the Organisation for Economic Co-operation and Development (OECD), serves as a critical international comparison tool that enables countries to review their policies and create strategic roadmaps (Ministry of National Education [MoNE], 2019).PISA assesses not only whether 15-year-old students can reproduce knowledge but also how they extrapolate from what they have learned and apply their knowledge in unfamiliar settings, both in and out of school (OECD, 2023). Beyond describing achievement patterns, large-scale assessments such as PISA play a central role in monitoring educational quality and informing system-level improvement strategies, particularly in periods of systemic disruption such as the post-pandemic era. In the PISA 2022 cycle, mathematics literacy was the major domain. Mathematics literacy is defined as the capacity to formulate, employ, and interpret mathematics in a variety of contexts to describe, explain, and predict phenomena (MoNE, 2023). According to PISA 2022 results, Türkiye ranked 39th among 81 countries with a score of 453; while this indicates an improvement compared to 2018, it remains significantly below the OECD average of 472 (Aksakal, 2024).

Social science research often involves investigating relationships between individuals and the environments in which they learn, live, and work (Hox et al., 2018). PISA data is inherently nested, with students clustered within schools. Consequently, traditional single-level analyses that ignore this hierarchical structure often disaggregate group-level variables to the individual level or aggregate individual-level variables to the group level (Hofmann, 1997). Such approaches violate independence assumptions and can lead to biased estimates (Julian, 2001; Muthén & Satorra, 1995). To address these methodological challenges, multilevel models provide a robust framework for simultaneously examining relationships at each level of the data hierarchy, thereby yielding more comprehensive and realistic results (Heck, 2001).

This study aims to examine the structural relationships between students' mathematics literacy and student- and school-level factors in order to provide evidence relevant to educational improvement and quality assurance processes in the Turkish education system. Furthermore, given that PISA 2022 was administered in the aftermath of the COVID-19 pandemic, this research seeks to uncover the variables influencing the education system during this extraordinary period. Specifically, the study addresses the following research questions:

1. Is there a significant difference in mathematics literacy among schools in the PISA 2022 Türkiye sample?
2. What are the student-level determinants of mathematics literacy?
3. What are the school-level determinants of mathematics literacy?
4. To what extent does the proposed multilevel model explain the variance in mathematics literacy, and what are the implications of these findings for system-level quality improvement?

The conceptual framework of the study is informed by ecological and multilevel perspectives on learning. From an ecological standpoint, student achievement is shaped by multiple, nested environments, including classroom and school contexts. Methodologically, the study is grounded in multilevel modelling theory, which explicitly accounts for the nested structure of educational data (Hox et al., 2018). Multilevel SEM extends traditional hierarchical linear modelling by allowing the estimation of latent variables, measurement error, and complex structural relations across levels simultaneously (Heck, 2001; Heck & Thomas, 2020). These features are particularly important when analysing PISA data, which rely on plausible values derived from item response theory and require the appropriate application of sampling weights to ensure valid population-level inferences.

Using Grade 4 data from the digitally administered TIMSS 2023 assessment, this study examines whether key instructional and motivational correlates of mathematics performance show similar patterns across education systems by comparing students in the United Arab Emirates (UAE) with students in four other GCC countries (Bahrain, Oman, Qatar, and Saudi Arabia).

Comparing the UAE with other GCC countries is informative because these systems share a broadly common regional policy context yet differ in how schooling is organized and resourced. Participation in TIMSS supports cross-system comparability in both achievement and questionnaire-based constructs (Mullis et al., 2021; von Davier, 2024). GCC countries nevertheless vary in reform trajectories and modernization efforts, which may shape how classroom experiences translate into competence beliefs and performance (World Bank, 2024). They also differ in demographic composition, such as the size and diversity of migrant and expatriate populations, which can influence school contexts and how self-belief measures function across settings. In addition, variation in digitalization and technology integration in schooling provides an important contextual background for interpreting how digital competence beliefs relate to learning outcomes (OECD, 2023). Overall, a UAE–other GCC comparison is both theoretically meaningful and policy-relevant for examining when digital self-efficacy and instructional clarity are more strongly linked to mathematics confidence and achievement.

The study focuses on three policy-relevant constructs available in TIMSS: instructional clarity in mathematics (students’ perceptions of clear and understandable instruction), digital self-efficacy (students’ perceived competence in using digital tools for learning), and confidence in mathematics (students’ competence beliefs). The conceptual framing relies primarily on Social Cognitive Theory (Bandura, 1997), which emphasizes self-efficacy beliefs as key determinants of learning-related behaviors and achievement, and Expectancy–Value Theory (Eccles & Wigfield, 2002), which suggests that competence beliefs (expectancies for success) shape engagement and performance outcomes. In addition, the focus on instructional clarity is consistent with research on effective teaching and teacher clarity as a predictor of student learning (Hattie, 2009).

A multi-group mediation (path) model is used to test whether confidence in mathematics functions as a mechanism linking instructional clarity and digital self-efficacy to mathematics achievement, and whether the strength of these direct and indirect pathways differs across the UAE and GCC contexts. This mediation logic is aligned with contemporary methodological guidance that emphasizes estimating and testing indirect effects directly in path/SEM frameworks (MacKinnon, 2008; Hayes, 2018). Because cross-system comparisons can mask meaningful contextual differences, the study uses multi-group SEM to estimate group-specific structural relations and formally compare pathways across contexts (Byrne, 2016; Kline, 2016). Gender is included as a covariate predicting both confidence and achievement in each group to account for potential gender-related differences in competence beliefs and performance (Else-Quest et al., 2010).

Four research questions guide the study: (1) How do digital self-efficacy and instructional clarity in mathematics predict Grade 4 mathematics achievement? (2) To what extent does confidence in mathematics mediate the relationships between digital self-efficacy and achievement, and between instructional clarity and achievement? (3) Do the direct structural relations among digital self-efficacy, instructional clarity, confidence, and achievement differ between the UAE and GCC groups? (4) Do the indirect effects via confidence differ between groups? Corresponding hypotheses specify positive direct effects of digital self-efficacy and instructional clarity on achievement and on confidence, a positive confidence-to-achievement link, and cross-group differences in selected pathways.

This proposal leverages TIMSS 2023 to test whether instructional and motivational pathways to mathematics achievement generalize across education systems, and to identify where associations differ by context. Findings can inform the interpretation of cross-system comparisons and efforts to strengthen early mathematics learning.

This proposal examines which school-level conditions are most strongly linked to mathematics success in Türkiye in PISA 2022. It uses the PISA 2022 School Questionnaire and supervised machine learning to model school success from leadership practices, school climate, resources, and family–school relations.

Research question

Which school-level factors best predict whether a school in Türkiye is “successful” in mathematics in PISA 2022, and how well can a supervised model classify school success using school-level indicators?

Objective

The objective is to build an interpretable predictive model and to identify actionable predictors that school leaders and policymakers can strengthen, while keeping sight of schools’ historical and social mission, as emphasized by Guevara-Reyes and his colleagues (2025).

Conceptual and theoretical framework
The framework combines leadership, school climate, and structural equity perspectives:

· Leadership and administration. School leaders shape learning conditions by setting goals, managing resources, and building a climate conducive to learning. Leadership influences student outcomes directly and indirectly through teacher quality, instructional coherence, and equitable learning climates (Leithwood & Jantzi, 2006; Robinson et al., 2008). In mathematics, instructional leadership, distributed leadership, and data-driven decision making are positively related to student performance (Hallinger, 2011). In developing countries, leaders often work under limited resources, unclear policy mandates, and fragmented teacher training systems, so leadership capacity matters for linking policy and classroom practices to improve attainment (Bush, 2009). Administrators can also support teacher collaboration and community engagement, which is an indirect predictor of mathematics performance (OECD, 2023).

· School climate. School climate (relationships, safety, and institutional values) shapes engagement and academic outcomes (Thapa et al., 2013). Self-Determination Theory and Stage-Environment Fit Theory emphasize how supportive contexts can meet students’ needs for competence, autonomy, and relatedness; positive teacher–student relationships can also buffer bullying and academic risks (Ren, Chen, & Zhao, 2025). Bullying undermines achievement by weakening students’ social bonds and sense of safety (Ren et al., 2025; Graham, 2016). International PISA evidence also shows that chronic absenteeism rose to 7.6% in PISA 2022, up from 4.7% in 2018 (OECD, 2023).

· Resources and equity. Cross-country PISA research suggests that school-to-school achievement gaps are smaller where resources are distributed more equally (Beese & Liang, 2010). School material resources and the quality of the learning environment show meaningful links to achievement in PISA-based studies (Trinidad, 2020). School-level safety, instructional leadership, and parental support also predict mathematics performance (Wardat et al., 2022; Tomul, Önder, & Taşlıdere, 2021).

European/international dimension

PISA is designed for international comparison, so identifying school-level predictors in Türkiye contributes to European and international discussions on equity, governance, and school improvement. The study defines school “Success” using an OECD-linked mathematics proficiency threshold used in OECD contexts (European Schools, 2022, p. 35), supporting interpretation across systems. The predictors prioritized by the model—parental involvement, disciplinary climate, technology use, leadership practices, student–teacher relationships, student absenteeism, and bullying—are widely relevant for equity-oriented school improvement efforts.

Method overview

The study analyzes 81 school-level features from 196 Turkish schools in the PISA 2022 School Questionnaire. To address class imbalance and small sample size, it applies Synthetic Minority Over-sampling Technique (SMOTE) and creates 3,564 balanced observations (Chawla et al., 2002). It tests supervised classifiers and reports logistic regression results; the final sample meets recommended minimums for stable modeling (Silvey & Liu, 2024). Generalizability is assessed using the training–test accuracy gap criterion (Géron, 2022).

Expected contribution

The study shows how interpretable machine learning can produce policy-relevant evidence from large international assessment data and highlight institutional levers linked to mathematics success (Acısıl-Çelik & YeşilKana, 2022; Erdoğan &Taştan, 2024).

Problem Statement

Large-scale assessments are standardized evaluations conducted at regional, national, or international levels with large student populations. They support teaching and learning by enabling cross-system comparisons and providing evidence for policy decisions such as curriculum reform, teacher professional development, and equitable resource allocation (Clarke & Luna-Bazaldua, 2021; Luo, 2023; Tan et al., 2024; Zhu et al., 2025). Among these assessments, the Programme for International Student Assessment (PISA), coordinated by the OECD, is one of the most influential. Conducted every three years since 2000, PISA measures the reading, mathematics, and science literacy of 15-year-olds worldwide (Luo, 2023; OECD, 2023a; Tan et al., 2024; Zhu et al., 2025). The PISA 2022 cycle focused on mathematics literacy, defined as the ability to reason mathematically and to apply mathematics to real-life contexts (OECD, 2023a). Persistent cross-national differences in achievement suggest that mathematics literacy is shaped by educational systems, cultural orientations, and inclusion policies (Bertling & Alegre, 2019; OECD, 2023a).

Prior research has examined multiple predictors of achievement, including motivation-related factors (e.g., self-efficacy, self-concept, interest, anxiety), language background, health-related factors, socio-economic status, safety and bullying, family resources, and teacher-related factors such as guidance, fairness, feedback, and experience (Martínez-Abad & Chaparro-Caso-López, 2016; Tan et al., 2024; Wan et al., 2025; Wang et al., 2023; Zhu et al., 2025). However, multidimensional constructs such as immigration and language exposure, school culture and climate, ICT familiarity, assessment systems, teacher qualifications, and global crises remain underexplored despite their relevance for understanding equity and learning opportunities (Bertling & Alegre, 2019).

This study focuses on Germany, Switzerland, and Türkiye due to their cultural and linguistic diversity in PISA 2022. Switzerland’s multilingual structure and substantial foreign-born population create unique educational dynamics (Eurydice, 2023), while Germany and Türkiye face comparable challenges related to immigration, language integration, and inclusion. These issues gained additional importance after the COVID-19 pandemic, which disrupted learning globally and highlighted inequalities in access, preparedness, and instructional continuity (Maldonado & De Witte, 2021; UNESCO, 2022). The pandemic also increased the relevance of teacher-developed assessment practices and teachers’ digital competence for sustaining mathematics learning (Scherer et al., 2021; Wellberg, 2023).

Methodologically, PISA datasets are highly suitable for educational data-mining approaches because they include large samples, multiple countries, and a wide range of student, family, teacher, and school-level variables. Data mining, referred to as knowledge discovery in databases, involves identifying meaningful patterns, structures, and relationships within large and complex datasets (Kretowski, 2019).

The purpose of this study is to compare the predictive performance of selected educational data-mining algorithms in classifying students’ PISA 2022 mathematics literacy performance and to identify the most influential predictors across Germany, Switzerland, and Türkiye. Also, this study aimed to examine whether PISA 2022 background variables (immigration and language exposure, school culture and climate, beliefs and attitudes, ESCS, ICT familiarity, teacher qualifications and professional development, assessment practices, and global crises) contribute to predicting students’ mathematics literacy outcomes across Switzerland, Germany, and Türkiye. Accordingly, the study addressed (1) the classification performance of C5.0 decision tree, random forest, Naive Bayes, and artificial neural network algorithms in predicting students’ PISA 2022 mathematics literacy performance and (2) the most influential predictors across the three contexts.