TIMSS 2019 Data

Data analysis

All statistics were computed using sampling weights.

All achievement data are presented as five plausible values. All required statistics were calculated separately for each of the plausible values and the resulting statistics averaged to get the result.

Standard errors for significance testing of achievement results were computed using:

  • The jackknife repeated replication (JRR) method to estimate sampling variance
  • Differences between the five plausible values to estimate measurement variance

General note: TIMSS data are designed for group-level reporting; students’ scale scores in the database are not suitable to measure performance of individual students or very small groups.

Secondary analysis

TIMSS data and the International Database are freely available.

For secondary analyses, data can be analyzed with IEA IDB Analyzer and the TIMSS 2019 International Database. These tools take into account the characteristics of the sampling and assessment design and implement the jackknife replication method with the appropriate plausible values.

Types of data files
  • Achievement items, including item information, IRT item parameters, and item percent correct statistics (see below under item release policy)
  • Background questionnaires (school, teacher, student, and home/early learning survey)
  • Curriculum questionnaires
  • Test-curriculum matching analysis (TCMA) data
Format(s) of data files
Item release policy

Responses to all items used in the assessment are included in the database; after each cycle, some of the assessment items are made available for restricted use by the public. The remaining items are kept secure, thus ensuring the possibility of measuring trends over time.  Access to the restricted-use items is subject to approval by IEA through its study data repository.  The response data for all items used in the assessment, however, are publicly and freely available in the data files.