Independent · non-commercial · publishes on a quarterly cycle|Current cycle 2026 Q3
Compound Evidence InstituteEvidence synthesis · established 2023Graded assessments of compounds, trials, methods and supply
Document set current to 30 July 2026
Defined term · Statistics and inference

Random-effects model

A pooling model assuming that true effects vary across studies and estimating their distribution. Produces wider intervals than a fixed-effect model and gives relatively more weight to small studies.

Document identifier
CEI-GT-075
Series
Defined term
Version
1.0
Published
30 Jul 2026
Last reviewed
30 Jul 2026
Certainty
Not rated

§1Random-effects model

§1.2Category

Statistics and inference — Terms describing how effects are estimated and how uncertainty is expressed.

§1.3Related terms

  • Fixed-effect model — A pooling model assuming a single true effect common to all contributing studies. Appropriate only where that assumption is defensible.
  • Heterogeneity — Variation in effect estimates across studies beyond that expected from chance. Quantified imperfectly by the I-squared statistic and assessed by inspection of the…
Nothing published by the Institute is medical advice, a diagnosis, a prescription, a treatment recommendation or a purchasing recommendation. Compounds supplied for research use are not approved for human or veterinary use in any jurisdiction, and a favourable analytical assessment of a supplier is not a statement that any product is safe or effective. The Institute publishes certainty ratings and never recommendations. No telephone number, messaging handle or ordering channel appears anywhere on this site.