PISA 2018 Data

Data analysis

All statistics are computed using sampling weights; standard errors based on balanced repeated replication weights are used for statistical significance and/or confidence intervals.

Analyses based on achievement test results (plausible values) are based on Rubin’s rule for multiply imputed variables.

The OECD average corresponds to the arithmetic mean of the respective country estimates.

Secondary analysis

The PISA data analysis manual provides SAS and SPSS codes to analyze PISA microdata.

User-written software is also available in Stata (repest, pisatools) and R (intsvy).

Basic statistics can be computed with the PISA Data Explorer

Types of data files
  • Student questionnaire data file (includes responses to parent questionnaire and optional student questionnaire, as well as plausible values for test achievement)
  • School questionnaire data file
  • Cognitive item response data file
  • Teacher questionnaire data file
  • Student questionnaire timing information data file (includes information about the time spent answering each questionnaire screen)
  • Financial literacy data file
  • Cognitive items total time/visits data file
Format(s) of data files
Item release policy

Most cognitive items are kept confidential for re-use in future cycles, to measure trends. A minority of items are released after each cycle to illustrate new frameworks and provide samples of tasks at different levels of proficiency.