Sequential Monitoring of Covariate-Adaptive Randomized Clinical Trials

Hu, Feifang; Hu, Hongjian

doi:10.5705/ss.202016.0330

Cited by 12 publications

(24 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This procedure requires us to adjust for the effect of covariates while constructing the test statistic. Similar conclusions can also be found in a simulation study by Zhu and Hu 24 . The sequential test statistic without adjustments to control the type I error rate only works well when all covariates are used in the data analysis.…”

Section: Statistical Inferencesupporting

confidence: 80%

“…Ma et al 9 have thoroughly studied the asymptotic properties of hypothesis testing under CAR designs with linear models and noted that the reduction of variance can be attributed to the balanced distributions of covariates across treatment groups. From this we were able to construct an adjusted test statistics that protects the desired type I error rate, and the simulation results in Zhu and Hu 24 certified the validity of this statistic. They also derived the asymptotic distribution of sequential test statistics under CAR designs in multiple scenarios in which full, partial, or none of the covariates were involved in inference.…”

Section: Introductionmentioning

confidence: 87%

“…Zhu and Hu 24 considered three different cases, namely, using all covariates, part of the covariates, or no covariates in analysis (ie, t ‐test). There are practical reasons to exclude some covariates from the analysis.…”

Section: Statistical Inferencementioning

confidence: 99%

“…There are several reasons for not using all covariates. It is not easy to interpret the practical significance of including certain covariates such as investigation sites; it will also lead to theoretical difficulties when using too many covariates, and the correct model specification is usually unknown in practice 24 . More importantly, the statistical inference under CAR design remains unclear.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sample size re‐estimation for covariate‐adaptive randomized clinical trials

2021

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

Covariate‐adaptive randomization (CAR) procedures have been developed in clinical trials to mitigate the imbalance of treatments among covariates. In recent years, an increasing number of trials have started to use CAR for the advantages in statistical efficiency and enhancing credibility. At the same time, sample size re‐estimation (SSR) has become a common technique in industry to reduce time and cost while maintaining a good probability of success. Despite the widespread popularity of combining CAR designs with SSR, few researchers have investigated this combination theoretically. More importantly, the existing statistical inference must be adjusted to protect the desired type I error rate when a model that omits some covariates is used. In this article, we give a framework for the application of SSR in CAR trials and study the underlying theoretical properties. We give the adjusted test statistic and derive the sample size calculation formula under the CAR setting. We can tackle the difficulties caused by the adaptive features in CAR and prove the asymptotic independence between stages. Numerical studies are conducted under multiple parameter settings and scenarios that are commonly encountered in practice. The results show that all advantages of CAR and SSR can be preserved and further improved in terms of power and sample size.

show abstract

Section: Statistical Inferencesupporting

confidence: 80%

Section: Introductionmentioning

confidence: 87%

Section: Statistical Inferencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sample size re‐estimation for covariate‐adaptive randomized clinical trials

2021

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…This simple approach avoids model misspecification but results in a conservative type I error rate under CAR (Shao et al, 2010). Hypothesis testing and sequential monitoring in clinical trials with CAR have recently been studied by Shao et al (2010), Ma et al (2015), Bugni et al (2018), and Zhu and Hu (2019). However, none of these studies investigated the application of CAR in seamless phase II/III trials.…”

Section: Introductionmentioning

confidence: 99%

Seamless Phase Ii/Iii Clinical Trials With Covariate Adaptive Randomization

Ma¹,

Wang²,

Zhu³

2022

STAT SINICA

View full text Add to dashboard Cite

There is an urgent need to evaluate new therapies in a time-sensitive and cost-effective manner. We propose the adaptive seamless phase II/III clinical trials with covariate adaptive randomization (CAR) to satisfy this urgent need. CAR is one of the most popular designs in randomized controlled trials; it enhances covariance balance and ensures valid treatment comparisons. The challenges include (1) the type I error rate of the commonly used Student's ttest following CAR can be inflated because of the seamless trials but decreased with CAR; (2) the complicated allocation mechanism induced by CAR causes extra difficulties to derive the asymptotic properties of a test procedure; and (3) previous theoretical studies of seamless trials mainly rely on the assumption of complete randomization, a procedure rarely used in real trials. We establish a theoretical foundation for adaptive seamless phase II/III trials with CAR. We also propose an approach that is easy to implement to control the type I error rate and to improve the power while the Student's t-test is employed. This is an important step that will promote the application of this procedure.

show abstract

Incorporating covariates information in adaptive clinical trials for precision medicine

Zhao

Wang

et al. 2021

Pharmaceutical Statistics

Self Cite

View full text Add to dashboard Cite

Precision medicine is the systematic use of information that pertains to an individual patient to select or optimize that patient's preventative and therapeutic care. Recent studies have classified biomarkers into predictive and prognostic biomarkers based on their roles in clinical studies. To design a clinical trial for precision medicine, predictive biomarkers and prognostic biomarkers should both be included. In statistical analysis, biomarkers are mathematically treated as covariates. We first classify covariates into predictive and prognostic covariates according to their roles. We then provide a brief review of recent advances in adaptive designs that incorporate covariates. However, the literature includes no designs that incorporate both prognostic covariates and predictive covariates simultaneously. In this paper, we propose a new family of covariate-adjusted response-adaptive (CARA) designs that incorporate both prognostic and predictive covariates and the responses. It is important to note that the predictive biomarkers and prognostic biomarkers play different roles in the new designs. The advantages of the proposed methods are demonstrated via numerical studies, and some further statistical issues are also discussed.

show abstract

Sequential Monitoring of Covariate-Adaptive Randomized Clinical Trials

Cited by 12 publications

References 38 publications

Sample size re‐estimation for covariate‐adaptive randomized clinical trials

Sample size re‐estimation for covariate‐adaptive randomized clinical trials

Seamless Phase Ii/Iii Clinical Trials With Covariate Adaptive Randomization

Incorporating covariates information in adaptive clinical trials for precision medicine

Contact Info

Product

Resources

About