Analyzing 2023 PIAAC Data Using R Package EdSurvey
This tutorial shows how to analyse PIAAC Cycle 2 data using the R package EdSurvey (Bailey et al., 2025), a comprehensive tool designed for large-scale assessment data. EdSurvey serves as a one-stop solution for processing, manipulation, and analysis of complex survey data. It automates the handling of plausible values, application of sampling weights, and variance estimation based on OECD-recommended methodologies. These are processes that would otherwise require substantial statistical expertise. Despite the complexity of such analyses, EdSurvey’s design keeps usage simple: for instance, running a regression with 80 replicate weights and 10 plausible values can be done in just a few lines of code. The package is also flexible, allowing users to rely on its built-in functions or to export data for use with other R packages. Moreover, EdSurvey is expansible, with ongoing enhancements to support a wider range of analyses and users with varying levels of expertise. Finally, by minimizing memory usage through selective data loading, EdSurvey efficiently handles large international datasets like PIAAC. Together, these features make it an indispensable tool for researchers and policy analysts working with large-scale assessment data.
Video 1.1 - Intro to PIAAC (Folien hier verfügbar)
A brief overview of PIAAC Cycle 2 data.
Zitation: Zhang, T. & Bailey, P. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 1.1 – Intro to PIAAC. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 1.2 - Weighting (Folien hier verfügbar)
An introduction to weighting concepts including sampling weights, replicate weights and the sampling variance estimation.
Zitation: Bailey, P. & Zhang, T. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 1.2 – Weighting. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 1.3 - Intro to Plausible Values (Folien hier verfügbar)
An introduction to plausible values, including why they are used and how to work with them.
Zitation: Zhang, T. & Bailey, P. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 1.3 – Intro to Plausible Values. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.1 - Intro to EdSurvey and Data Processing (Folien hier verfügbar)
An overview of EdSurvey, with guidance on installing the package and importing PIAAC data.
Zitation: Bailey, P. & Zhang, T. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.1 – Intro to EdSurvey and Data Processing. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.2 - Data Manipulation (Folien hier verfügbar)
Methods for extracting selected information for data manipulation before analyzing it with EdSurvey.
Zitation: Bailey, P. & Zhang, T. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.2 – Data Manipulation. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.3 - Summary Statistics (Folien hier verfügbar)
Getting summary statistics for variables or plausibel values.
Zitation: Bailey, P. & Zhang, T. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.3 – Summary Statistics. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.4 - EdSurvey Table (Folien hier verfügbar)
Creating a stratified summary table of an outcome variable by one or more categorical variables.
Zitation: Zhang, T. & Bailey, P. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.4 – EdSurvey Table. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.5 - Proficiency levels (Folien hier verfügbar)
Calculating proficiency levels in discrete or cumulative ways.
Zitation: Zhang, T. & Bailey, P. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.5 – Proficiency levels. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.6 - Percentiles (Folien hier verfügbar)
Obtaining percentiles for plausible values or continuous variables.
Zitation: Zhang, T. & Bailey, P. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.6 – Percentiles. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.7 - Gap Analysis (Folien hier verfügbar)
Comparing groups or countries using the Cycle 2 data.
Zitation: Zhang, T. & Bailey, P. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.7 – Gap Analysis. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.8 - Linear Regression (Folien hier verfügbar)
Conduct linear regressions with plausible values.
Zitation: Bailey, P. & Zhang, T. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.8 – Linear Regression. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
Video 2.9 - Logistic Regression (Folien hier verfügbar)
Conduct logistic regression with or without plausible values.
Zitation: Bailey, P. & Zhang, T. (2025). Analyzing 2023 PIAAC Data Using R Package EdSurvey. Online Tutorial, Video 2.9 – Logistic Regression. GESIS –Leibniz Institute for the Social Sciences, Mannheim. Available at https://www.gesis.org/data-on-adult-education/workshops
