rpact-com / rpact

rpact: Confirmatory Adaptive Clinical Trial Design and Analysis
https://rpact-com.github.io/rpact/
23 stars 5 forks source link

`summary()` for count simulations #53

Closed danielinteractive closed 1 month ago

danielinteractive commented 1 month ago
+Simulation in a count data design

Sequential analysis with a maximum of 3 looks (group sequential design), 
one-sided overall significance level 2.5%.
+The results were simulated for a two-sample Wald-test (normal approximation), 
+H0: lambda(1) / lambda(2) = 1 *Theta H0*, power directed towards larger values, 
+H1: effect as specified, overdispersion = 1, 
planned cumulative sample size = c(40, 80, 120), 
+planned calendar times = c(X, X, X),
+accrual time,
+fixed *OR* variable follow-up time, *Order see sim survival*
simulation runs = 1000, 
seed = -298806844.

Stage                                                 1      2      3 
Planned information rate                          33.3%  66.7%   100% 
Efficacy boundary (z-value scale)                 3.471  2.454  2.004 
Stage levels (one-sided)                         0.0003 0.0071 0.0225 
Cumulative power, alt. = 0                            0 0.0070 0.0260 *effect size ratio OR lambda*
Cumulative power, alt. = 0.2                     0.0020 0.0650 0.2220 
Cumulative power, alt. = 0.4                     0.0060 0.2170 0.5470 
Cumulative power, alt. = 0.6                     0.0630 0.5810 0.8870 
Cumulative power, alt. = 0.8                     0.1780 0.8490 0.9880 
Cumulative power, alt. = 1                       0.3850 0.9840 1.0000 
Stagewise number of subjects, alt. = 0             40.0   40.0   40.0 
Stagewise number of subjects, alt. = 0.2           40.0   40.0   40.0 
Stagewise number of subjects, alt. = 0.4           40.0   40.0   40.0 
Stagewise number of subjects, alt. = 0.6           40.0   40.0   40.0 
Stagewise number of subjects, alt. = 0.8           40.0   40.0   40.0 
Stagewise number of subjects, alt. = 1             40.0   40.0   40.0 
Expected number of subjects under H1, alt. = 0    119.7 
Expected number of subjects under H1, alt. = 0.2  117.3 
Expected number of subjects under H1, alt. = 0.4  111.1 
Expected number of subjects under H1, alt. = 0.6   94.2 
Expected number of subjects under H1, alt. = 0.8   78.9 
Expected number of subjects under H1, alt. = 1     65.2 
Conditional power (achieved), alt. = 0                  0.0614 0.0590 *does not yet exist*
Conditional power (achieved), alt. = 0.2                0.1665 0.2179 
Conditional power (achieved), alt. = 0.4                0.3083 0.3925 
Conditional power (achieved), alt. = 0.6                0.5192 0.6181 
Conditional power (achieved), alt. = 0.8                0.6872 0.7320 
Conditional power (achieved), alt. = 1                  0.8433 0.8490 
Exit probability for efficacy, alt. = 0               0 0.0070 0.0190 
Exit probability for efficacy, alt. = 0.2        0.0020 0.0630 0.1570 
Exit probability for efficacy, alt. = 0.4        0.0060 0.2110 0.3300 
Exit probability for efficacy, alt. = 0.6        0.0630 0.5180 0.3060 
Exit probability for efficacy, alt. = 0.8        0.1780 0.6710 0.1390 
Exit probability for efficacy, alt. = 1          0.3850 0.5990 0.0160 

Legend:
  alt.: alternative

Use getSimulationRates() as template.

fpahlke commented 1 month ago

Implemented