Table 2.
Dose (mg/kg bw) | N | Geometric mean (g) | ES (%) | Lower 95% confidence bound (one sided) of ES (%)a | Upper 95% confidence bound (one sided) of ES (%)a | t‐statistic | p‐value |
---|---|---|---|---|---|---|---|
0 | 10 | 26.3 | |||||
8 | 10 | 26.0 | −1.3 | −5.7 | 3.3 | 0.491 | 0.31 |
25 | 10 | 25.7 | −2.6 | −6.9 | 2.0 | 0.962 | 0.17 |
76 | 10 | 26.3 | −0.24 | −4.7 | 4.4 | 0.087 | 0.47 |
215 | 10 | 25.0 | −5.1 | −9.4 | −0.71 | 1.93 | 0.029 |
419 | 10 | 20.8 | −21 | −25 | −17 | 8.64 | 0.000 |
ES: effect size (in per cent change compared to response at dose zero).
Two‐sided 90% confidence interval was calculated for the difference on log‐scale, and then transformed back, resulting in the confidence interval for per cent change (see Slob (2002) for further statistical assumptions).