Research Workbench

Meta-analysis subgroup Q partition

Partition fixed-weight heterogeneity into within- and between-subgroup components.

Your entries stay in this page’s memory and are not submitted to us. Downloads are generated locally. Reloading or leaving the page clears your entries. Do not enter patient information.

Use 2–10 named subgroups with at least two studies each; estimates must share a scale and SEs must be positive. Labels are case-sensitive.

The starting values are hypothetical. Results update as you edit. Use aggregate or synthetic inputs only.

Calculation results

Total Q
15.025
Within-subgroup Q
0.625
Between-subgroup Q
14.4
Between df
1
Approximate interaction p
0.00014780231

How to interpret the output

With common inverse-variance weights, Qbetween=Qtotal−sum(Qwithin). The chi-square approximation uses groups−1 degrees of freedom. This ecological subgroup comparison is vulnerable to confounding, low power and multiplicity. It is not an individual-level treatment interaction or a random-effects subgroup test.

Method reference

Source checked 2026-11-06. Read the reproducible calculator validation report.