Description Usage Arguments Value References See Also Examples
Compute the baseline parameters ζ_0^2 and \boldsymbolδ_0
needed for sample size calculation for standard win ratio test (see WRSS
).
The calculation is based
on a Gumbel–Hougaard copula model for survival time D^{(a)} and nonfatal event
time T^{(a)} for group a (1: treatment; 0: control):
{P}(D^{(a)}>s, T^{(a)}>t) =\exp≤ft(-≤ft[≤ft\{\exp(aξ_1)λ_Ds\right\}^κ+ ≤ft\{\exp(aξ_2)λ_Ht\right\}^κ\right]^{1/κ}\right),
where ξ_1 and ξ_2 are the component-wise log-hazard ratios to be used
as effect size in WRSS
.
We also assume that patients are recruited uniformly over the period [0, τ_b]
and followed until time τ (τ≥qτ_b), with an exponential
loss-to-follow-up hazard λ_L.
1 |
lambda_D |
Baseline hazard λ_D for death. |
lambda_H |
Baseline hazard λ_H for nonfatal event. |
kappa |
Gumbel–Hougaard copula correlation parameter κ. |
tau_b |
Length of the initial (uniform) accrual period τ_b. |
tau |
Total length of follow-up τ. |
lambda_L |
Exponential hazard rate λ_L for random loss to follow-up. |
N |
Simulated sample size for monte-carlo integration. |
seed |
Seed for monte-carlo simulation. |
A list containing real number zeta2
for ζ_0^2
and bivariate vector delta
for \boldsymbolδ_0.
Mao, L., Kim, K. and Miao, X. (2021). Sample size formula for general win ratio analysis. Biometrics, https://doi.org/10.1111/biom.13501.
1 | # see the example for WRSS
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.