Pre-licensure Vaccine Trial Power calculator
Power Calculator
Boundary and Plot
This tool searches through a space of design boundaries (scalar values $b_0$ and $b_1$) to find values that achieve the approximate specified type I and type II errors for the sequential Generalized Likelihood Ratio (GLR) test of $p_0$ versus $p_1$ in pre-licensure vaccine trials; see
Sequential generalized likelihood ratio tests for vaccine safety evaluation
(pp 2698–2708) by Mei-Chiung Shih, Tze Leung Lai, Joseph F. Heyse and Jie Chen
DOI: 10.1002/sim.4036
Once $(b_0, b_1)$ are chosen, the sample size and a user-friendly plot and boundary specification in terms of number of adverse events can be computed using the other tab.
1a. Null Hypothesis $p_0$ $\in(0,1)$:
1b. Alternative Hypothesis $p_1 > p_0$ $\in (0,1)$ (a value close to $p_0$ is very compute intensive!):
2. Significance Level $\alpha$ $\in [0.01, 0.15]$:
3. Type II Error $\beta$ $\in [0.01, 0.75]$:
4. Search step size $> 0$:
5. Tolerance $\in [10^{-3}, 10^{-7}]$:
6. Maximum number of iterations ($\geq 4$ but $\leq 100$):
7. Number of grid points ($\geq 3$ but $\leq 10$):
This tool computes the boundary in field-usable form in terms of the number of adverse events and provides a visual plot, once $(b_0, b_1)$ are chosen from the previous tab; see
Sequential generalized likelihood ratio tests for vaccine safety evaluation
(pp 2698–2708) by Mei-Chiung Shih, Tze Leung Lai, Joseph F. Heyse and Jie Chen
DOI: 10.1002/sim.4036
1a. Null Hypothesis $p_0$ $\in(0,1)$:
1b. Alternative Hypothesis $p_1 > p_0$ $\in (0,1)$ (a value close to $p_0$ is very compute intensive!):
2. Rejection Boundary $b_0$:
3. Acceptance Boundary $b_1$:
4. Tolerance $\in [10^{-3}, 10^{-7}]$:
Submit
Type I Error $\alpha$ for GLR boundaries
Type II Error $\beta$ for GLR boundaries
Boundary Plot
Estimated Type I and Type II Errors
Maximum Total Number of AEs Needed
Boundary in terms of Number of Vaccine Adverse Events