Analysis of educational data 2400-ZEWW1032
The course focuses on the empirical analysis of data from large-scale international educational assessments (PISA, TIMSS). The main topics covered include:
1. Introduction to Educational Data
o Characteristics of data from ILSA (International Large-Scale Assessments)
o Structure of data files (student, school, country-level files, and codebooks)
2. Plausible Values (PVs)
o Definition and rationale for their use
o Averaging across plausible values
o Using plausible values in regression analyses
3. Replicate Weights
o The role of weights in ensuring representativeness
o Differences between various types of weights (e.g., senate weights, replicate weights)
o Implementation of BRR and Fay’s BRR weights in STATA
4. Data Analysis – Regression Models
o Simple and multiple regression models
o Hypothesis testing and interpretation of results
o Regression models with interactions and prediction of outcomes
5. Data Analysis – Multilevel Models
o Random-effects models (students nested within schools)
o Addressing the hierarchical structure of educational data
o Random-slope models
6. Index Construction
o Factor Analysis (FA)
o Item Response Theory (IRT)
o Latent Class Analysis (LCA)
7. Data Visualization
o Graphing commands in STATA
o Regression plots, scatterplots, and boxplots
8. Reporting Results
o Exporting results to Word and Excel
o Preparing analytical reports
Course coordinators
Type of course
Learning outcomes
Knowledge
Upon successful completion of the course, students:
1. Understand the characteristics of data from international large-scale educational assessments (ILSAs), such as PISA and TIMSS, including data file structures and variable coding schemes.
2. Understand the concept of Plausible Values (PVs) and their role in the analysis of educational achievement data.
3. Possess knowledge of replicate weighting methods and their importance in ensuring the representativeness and validity of statistical estimates.
4. Understand the fundamentals of regression modeling, including interaction effects and multilevel models.
5. Understand the principles of quantitative data visualization using STATA.
Skills
Upon successful completion of the course, students are able to:
1. Independently prepare, import, and manage ILSA datasets within an analytical environment.
2. Conduct statistical analyses that appropriately incorporate plausible values and replicate weights.
3. Interpret analytical results, including hypothesis testing and the evaluation of interaction effects.
Social Competencies
Upon successful completion of the course, students:
1. Are able to critically evaluate data quality and the results of empirical analyses in the context of educational research.
2. Are able to collaborate effectively within an analytical team in preparing reports and presenting the results of quantitative research.
Assessment criteria
• 20% – Class participation and homework assignments
• 40% – Group project involving the analysis of educational data
• 40% – Final examination (multiple-choice test)
Bibliography
OECD (2019). PISA 2018 Technical Report
Rutkowski, L., Gonzalez, E., Joncas, M., & Von Davier, M. (2010). International large-scale assessment data: Issues in secondary analysis and reporting. Educational researcher, 39(2), 142-151.