Skip to content

Matrix sampling with planned missingness in large-scale assessments

Research Method · All research methods
Evidence · no claims cited

Description

Large-scale assessments organize items into testlets counterbalanced across students within a sampling frame, so that 'no student ever takes the entire battery of assessments, or even all the items on any one test'. In PISA, 'each student participates for 2 h, seeing only a fraction of the total set of test items', and for optional domains many students see no items yet still receive PVs. This design makes individual-level scoring from item responses impossible and necessitates the PV methodology.

Accounts

  • Matrix sampling with planned missingness in large-scale assessments (e.g., PISA testlets counterbalanced across students): Large-scale assessments organize items into testlets counterbalanced across students within a sampling frame, so that 'no student ever takes the entire battery of assessments, or even all the items on any one test'. In PISA, 'each student participates for 2 h, seeing only a fraction of the total set of test items', and for optional domains many students see no items yet still receive PVs. This design makes individual-level scoring from item responses impossible and necessitates the PV methodology. (Dumas et al. (2026))

Claims

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
Page metadata
Field Value
type research-method
id matrix-sampling-with-planned-missingness-in-large-scale-assessments
title Matrix sampling with planned missingness in large-scale assessments
description Large-scale assessments organize items into testlets counterbalanced across students within a sampling frame, so that 'no student ever takes the entire battery of assessments, or even all the items on any one test'.
status review
generated by process:settle-candidates on 2026-10-19
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.