This is an archived version. For the current version, please go to

9.6.5  Selection of study characteristics for subgroup analyses and meta-regression

Introductory text  Ensure that there are adequate studies to justify subgroup analyses and meta-regressions  Specify characteristics in advance  Select a small number of characteristics  Ensure there is scientific rationale for investigating each characteristic  Be aware that the effect of a characteristic may not always be identified  Think about whether the characteristic is closely related to another characteristic (confounded)