How credible is the subgroup finding?
| Questions |
| Is the subgroup variable a characteristic specified at the time of the design of the study? |
| Was the correct direction of the subgroup effect (favorable or unfavorable to treatment for example) specified a priori? |
| Is the significant interaction effect independent of other potential subgroup effects? |
| Does the interaction test suggest a low likelihood that chance can explain the apparent subgroup effect? |
| Was the subgroup effect 1 of a small number of hypothesized effects tested? (The greater the number of hypotheses tested, the greater the number of subgroup effects one will discover by chance.) |
| Is the magnitude of the subgroup effect large? |
| Is the interaction consistent across closely related outcomes within the study? |
| Is the interaction consistent across studies? |
| Are the subgroup effects plausible? Is there a biologic rationale? |