August 2015
The pursuit of balance: an overview of covariate-adaptive randomization techniques in clinical trials

Yunzhi Lin,MingZhu,ZhengSu
Contemporary Clinical Trials
access article here
a b s t r a c t

Randomization is fundamental to thedesign and conduct of clinical trials. Simple randomization ensuresindependence among subject treatment assignments and prevents potentialselection biases, yet it does not guarantee balance in covariate distributionsacross treatment groups. Ensuring balance in important prognostic covariatesacross treatment groups is desirable for many reasons. A broad class ofrandomization methods for achieving balance are reviewed in this paper; theseinclude block randomization, stratified randomization, minimization, anddynamic hierarchical randomization. Practical considerations arising fromexperience with using the techniques are described. A review of randomizationmethods used in practice in recent randomized clinical trials is also provided.

Clinical trials; Randomization; Block randomization; Stratified randomization;Minimization; Dynamic hierarchical randomization