Impact of minimal sufficient balance, minimization, and stratified permuted blocks on bias and power in the estimation of treatment effect in sequential clinical trials with a binary endpoint.
Impact of minimal sufficient balance, minimization, and stratified permuted blocks on bias and power in the estimation of treatment effect in sequential clinical trials with a binary endpoint.
复制标题
DOI：
10.1177/09622802211055856
复制
发表时间：
2022-01
影响因子：
2.3
通讯作者：
中科院分区：
文献类型：
--
作者：
最小化是临床试验随机化阶段控制基线协变量失衡的最常用方法之一。以往的研究发现，最小化不能像其他方法一样保持分配的随机性，比如最小充分平衡，这使得它更容易受到分配可预测性和选择偏差的影响。此外，在模拟研究中显示，当使用适度偏倚硬币概率（≤0.65）时，最小化无法充分控制严重的协变量失衡。本研究将随机化方法的研究扩展到分析阶段，比较治疗分配方法对使用logistic回归估计治疗效果对二元结局的功效和偏倚的影响。在未校正分析中，发现完全随机化、最小化和最小充分平衡之间治疗效应估计的把握度和偏倚相当。此外，在协变量调整分析中，发现最低限度的充分平衡对把握度的影响最小，偏倚最小。当进行协变量自适应受试者随机化时，建议在临床试验中使用最小充分平衡法作为最小化的替代方法。
Minimization is among the most common methods for controlling baseline covariate imbalance at the randomization phase of clinical trials. Previous studies have found that minimization does not preserve allocation randomness as well as other methods, such as minimal sufficient balance, making it more vulnerable to allocation predictability and selection bias. Additionally, minimization has been shown in simulation studies to inadequately control serious covariate imbalances when modest biased coin probabilities (≤0.65) are used. This current study extends the investigation of randomization methods to the analysis phase, comparing the impact of treatment allocation methods on power and bias in estimating treatment effects on a binary outcome using logistic regression. Power and bias in the estimation of treatment effect was found to be comparable across complete randomization, minimization, and minimal sufficient balance in unadjusted analyses. Further, minimal sufficient balance was found to have the most modest impact on power and the least bias in covariate-adjusted analyses. The minimal sufficient balance method is recommended for use in clinical trials as an alternative to minimization when covariate-adaptive subject randomization takes place.
登录
查看更多内容
DOI：
10.1016/0197-2456(85)90120-5
发表时间：
1985-01-01
期刊：
CONTROLLED CLINICAL TRIALS
影响因子：
--
作者：
BIRKETT, NJ
通讯作者：
BIRKETT, NJ
影响因子：
2.3
作者：
Ciolino, Jody D.;Martin, Renee H.;Palesch, Yuko Y.
通讯作者：
Palesch, Yuko Y.
影响因子：
2.7
作者：
ATKINSON, AC
通讯作者：
ATKINSON, AC
影响因子：
1.8
作者：
FORSYTHE, AB
通讯作者：
FORSYTHE, AB
影响因子：
2.2
作者：
Ciolino J;Zhao W;Martin R;Palesch Y
通讯作者：
Palesch Y