Use purpose-built software tools and read the assessment's technical documentation before secondary analysis of PVs¶

Strategy · All strategies
Evidence · 2 claims (2 for) · 1 study (1 theoretical), q1 · 0 of 1 report an effect size · 2 claims rest on one study

Description¶

Because different large-scale assessments employ different sampling procedures and conditioning models, the article advises analysts to 'carefully read[ ] the methodological and technical details available from the research team who produced the PVs before beginning a secondary analysis'. R packages like survey and intsvy, plus OECD analysis guides in SPSS and SAS, make the complex analytic steps straightforward.

Design Implications¶

Context¶

Requirements¶

• Access the assessment program's technical documentation and use software that implements weighting and Rubin's-rules aggregation

Constraints¶

• No single methodological guide is equally applicable across all large-scale assessments because their conditioning models differ

Target Learners¶

• educational researchers beginning to work with large-scale assessment data

Target Learning Goals¶

• conducting methodologically sound secondary analysis of PV data

Claims¶

• Plausible values in large-scale assessment datasets are model-imputed draws from a posterior distribution, not individual test scores [+W]
• Person-centered clustering of students on plausible values falls outside the valid use of PVs, while clustering sampling-frame units is valid [+W]

Related Strategies¶

Examples¶

-

Key Sources¶

• Dumas, D., Goecke, B., Kagan, S., & Weiss, S. (2026). Zooming Out On Education: Making Valid Psychological Inferences From Large-Scale Assessment Data. Educational Psychology Review. https://doi.org/10.1007/s10648-025-10110-7