Table 1. Upper bound on treatment effect heterogeneity compatible with the results.
| Any distribution | Normal distribution | Dichotomous response | ||
|---|---|---|---|---|
| ρ | SDte (HAMD17) | % of patients with TE > 7 HAMD17 | Responder TE (HAMD17) | % Responders |
| -1.0 | 15.5 | 37.3 | 9.7 | 20.5 |
| -0.8 | 12.4 | 34.4 | 8.2 | 24.3 |
| -0.6 | 9.4 | 29.8 | 6.7 | 29.8 |
| -0.4 | 6.5 | 22.1 | 5.2 | 38.1 |
| -0.2 | 3.7 | 8.9 | 3.9 | 51.9 |
| 0.0 | 1.5 | 0.1 | 2.8 | 72.2 |
| 0.2 | 0.6 | 0.0 | 2.3 | 86.2 |
| 0.4 | 0.4 | 0.0 | 2.2 | 91.6 |
| 0.6 | 0.3 | 0.0 | 2.1 | 94.1 |
| 0.8 | 0.2 | 0.0 | 2.1 | 95.5 |
| 1.0 | 0.2 | 0.0 | 2.1 | 96.3 |
Assuming a VR of 1.02, a SDp of 7.66 points (based on Cipriani [10]) and different correlation coefficients ρ between the response under placebo and the treatment effect. Left column (“any distribution”): Upper bounds for the standard deviation of the treatment effect. Mid column: Percentage of patients with TE greater than 7 HAMD17 points, when assuming a normal distribution of the TE with mean 2.0. Right column (“dichotomous response”): Patients are either “non-responders” with a treatment effect of 0, or "responders” with the responder treatment effect. For a given correlation coefficient ρ, there is one possible solution for the treatment effect (TE).