Skip navigation

The consumer's guide to subgroup analysis

The Annals of Internal Medicine carried a very important article in 1992 on "the extent to which a clinician should believe and act on the results of subgroup analyses of data from randomised controlled trials or meta-analyses". The authors pointed out that the extent was controversial and they provided guidelines for making decisions about the validity and relevance of subgroup analysis.

In classic McMaster style they gave a simple table of guidelines. The article is set out so that each of the questions in the box is answered and there is a very useful list of references at the end. Anyone working with clinicians and trying to encourage clinicians to make better use of trial and meta-analysis data would be well advised to read this excellent paper.

Guidelines for deciding whether apparent differences in subgroup response are real

  1. Is the magnitude of the difference clinically important?
  2. Was the difference statistically significant?
  3. Did the hypothesis precede rather than follow the analysis?
  4. Was the subgroup analysis one of a small number of hypotheses tested?
  5. Was the difference suggested by comparisons within rather than between studies?
  6. Was the difference consistent across studies?
  7. Is there indirect evidence that supports the hypothesised difference?
AD Oxman, GH Guyatt. Annals of Internal Medicine 1992 116:78-84.

previous or next story in this issue