A roadmap to using randomization in clinical trials

Abstract

Background Randomization is the foundation of any clinical trial involving treatment comparison. It helps mitigate selection bias, promotes similarity of treatment groups with respect to important known and unknown confounders, and contributes to the validity of statistical tests. Various restricted randomization procedures with different probabilistic structures and different statistical properties are available. The goal of this paper is to present a systematic roadmap for the choice and application of a restricted randomization procedure in a clinical trial. Methods We survey available restricted randomization procedures for sequential allocation of subjects in a randomized, comparative, parallel group clinical trial with equal (1:1) allocation. We explore statistical properties of these procedures, including balance/randomness tradeoff, type I error rate and power. We perform head-to-head comparisons of different procedures through simulation under various experimental scenarios, including cases when common model assumptions are violated. We also provide some real-life clinical trial examples to illustrate the thinking process for selecting a randomization procedure for implementation in practice. Results Restricted randomization procedures targeting 1:1 allocation vary in the degree of balance/randomness they induce, and more importantly, they vary in terms of validity and efficiency of statistical inference when common model assumptions are violated (e.g. when outcomes are affected by a linear time trend; measurement error distribution is misspecified; or selection bias is introduced in the experiment). Some procedures are more robust than others. Covariate-adjusted analysis may be essential to ensure validity of the results. Special considerations are required when selecting a randomization procedure for a clinical trial with very small sample size. Conclusions The choice of randomization design, data analytic technique (parametric or nonparametric), and analysis strategy (randomization-based or population model-based) are all very important considerations. Randomization-based tests are robust and valid alternatives to likelihood-based tests and should be considered more frequently by clinical investigators.

Non-Invasive Transcutaneous Vagus Nerve Stimulation for the Treatment of Fibromyalgia Symptoms: A Study Protocol

“…The data of the recruited participants will be included in a secure database, and a code per group for randomization will be generated. To allocate subjects to each group with complete randomness and independence regarding the intervention, simple randomization will be applied [ 66 ], by which the participant codes will be assigned to the respective groups via a 1:1 randomization procedure (equal allocation) [ 67 , 68 ] using the computer spreadsheet Microsoft Excel.…”

Randomizing a clinical trial in neuro-degenerative disease

“…Ryeznik and Sverdlov [8, §3.3] suggest a quantification of the distance from the (bias, normalized loss) point to the unachievable origin (0,0), which is the “ideal point” for the two criteria. See also Berger et al [44] . They suggest a scaled Euclidean distance, which we rescale by to give the measure for which R and D both have the value 1.…”

Correlation between Bone Mineral Density and Progression of Hip Osteoarthritis in Adult Men and Women in Bulgaria—Results from a 7-Year Study

“…The sample size of each patient group and subgroup was calculated using the methodology described by J. Wittes [ 44 ], considering a 2% possible loss of patients in the treatment groups, as compared to 1% in the control group. Restricted block randomization [ 45 ] was applied during the screening and selection process, resulting in the formation of the following six blocks: K/L-II’A’; K/L-II’I’; K/L-II’H’; K/L-III’A’; K/L-III’I’; and K/L-III’H’. From each block of 50 patients, subgroups with a fixed female to male ratio (15/10) were randomly generated using a computer program ( Table 1 ).…”