Pseudo cluster randomization: a treatment allocation method to minimize contamination and selection bias

In some clinical trials, treatment allocation on a patient level is not feasible, and whole groups or clusters of patients are allocated to the same treatment. If, for example, a clinical trial is investigating the efficacy of various patient coaching methods and randomization is done on a patient level, then patients who are receiving different methods may come into contact with each other and influence each other. This would create contamination of the treatment effects. Such bias might be prevented by randomization on the coaches level. The patients of a coach constitute a cluster and all the subjects in that cluster receive the same treatment. Disadvantages of this approach may be reduced statistical efficiency and recruitment bias, as the treatment that a subject will receive is known in advance. Pseudo cluster randomization avoids this, because in pseudo cluster randomization, not everybody in a certain cluster receives the same treatment, just the majority. There are two groups of clusters: in one group the majority of subjects receive treatment A, while a limited number receive treatment B. In the other group of clusters the proportions are reversed. The statistical properties of this method are described. When contamination is present, the method appears to be more efficient than randomization on a patient level or on a cluster level.     

Comparison of randomization techniques for clinical trials with data from the HOMERUS-trial

Background. Several methods of randomization are available to create comparable intervention groups in a study. In the HOMERUS-trial, we compared the minimization procedure with a stratified and a non-stratified method of randomization in order to test which one is most appropriate for use in clinical hypertension trials. A second objective of this article was to describe the baseline characteristics of the HOMERUS-trial. Methods. The HOMERUS population consisted of 459 mild-to-moderate hypertensive subjects (54% males) with a mean age of 55 years. These patients were prospectively randomized with the minimization method to either the office pressure (OP) group, where antihypertensive treatment was based on office blood pressure (BP) values, or to the self-pressure (SP) group, where treatment was based on self-measured BP values. Minimization was compared with two other randomization methods, which were performed post-hoc: (i) non-stratified randomization with four permuted blocks, and (ii) stratified randomization with four permuted blocks and 16 strata. In addition, several factors that could influence outcome were investigated for their effect on BP by 24-h ambulatory blood pressure monitoring (ABPM). Results. Minimization and stratified randomization did not lead to significant differences in 24-h ABPM values between the two treatment groups. Non-stratified randomization resulted in a significant difference in 24-h diastolic ABPM between the groups. Factors that caused significant differences in 24-h ABPM values were: region, centre of patient recruitment, age, gender, microalbuminuria, left ventricular hypertrophy and obesity. Conclusion. Minimization and stratified randomization are appropriate methods for use in clinical trials. Many outcome factors should be taken into account for their potential influence on BP levels. Recommendation. Due to the large number of potential outcome factors that can influence BP levels, minimization should be the preferred method for use in clinical hypertension trials, as it has the potential to randomize more outcome factors than stratified randomization.     

Gold is not always good enough: the shortcomings of randomization when evaluating interventions in small heterogeneous samples

The three criteria for valid inference in therapeutic intervention evaluation are achieving control, avoiding systematic error, and minimizing random error. The randomized, double-blind, controlled trial has appropriately been accepted as the methodological gold standard because it is the only method with the potential to avoid systematic error resulting from unbalanced distributions of recognized and unrecognized determinants of outcome. This potential is not always realized, however, particularly with small, heterogeneous patient samples—which undermines the rationale for randomization in these circumstances. Minimization is one possible strategy to attain validity in such circumstances, but the acceptability of nonrandomized strategies is currently hampered by deference to the concept of randomization. For each intervention evaluation, research design should be considered afresh, focusing on the criteria determining validity rather than particular methodological elements.     

Misrepresenting random sampling? A systematic review of research papers in the Journal of Advanced Nursing

AIM: This paper discusses the theoretical limitations of the use of random sampling and probability theory in the production of a significance level (or P-value) in nursing research. Potential alternatives, in the form of randomization tests, are proposed. BACKGROUND: Research papers in nursing, medicine and psychology frequently misrepresent their statistical findings, as the P-values reported assume random sampling. In this systematic review of studies published between January 1995 and June 2002 in the Journal of Advanced Nursing, 89 (68%) studies broke this assumption because they used convenience samples or entire populations. As a result, some of the findings may be questionable. DISCUSSION: The key ideas of random sampling and probability theory for statistical testing (for generating a P-value) are outlined. The result of a systematic review of research papers published in the Journal of Advanced Nursing is then presented, showing how frequently random sampling appears to have been misrepresented. Useful alternative techniques that might overcome these limitations are then discussed. REVIEW LIMITATIONS: This review is limited in scope because it is applied to one journal, and so the findings cannot be generalized to other nursing journals or to nursing research in general. However, it is possible that other nursing journals are also publishing research articles based on the misrepresentation of random sampling. The review is also limited because in several of the articles the sampling method was not completely clearly stated, and in this circumstance a judgment has been made as to the sampling method employed, based on the indications given by author(s). CONCLUSION: Quantitative researchers in nursing should be very careful that the statistical techniques they use are appropriate for the design and sampling methods of their studies. If the techniques they employ are not appropriate, they run the risk of misinterpreting findings by using inappropriate, unrepresentative and biased samples.     

Personalizing medicine: a review of adaptive treatment strategies

Much of current pharmacological practice focuses on identifying the single ‘best’ treatment (or course of treatments) for a particular disease. Recently, however, focus has begun to shift towards a more patient‐centric rather than disease‐centric approach, where personal characteristics are used to identify the optimal treatment for an individual. Adaptive treatment strategies (also known as dynamic treatment regimes) are part of a rapidly expanding area of research whereby such personalized treatments can be identified. These methods can lead to improved results over standard ‘one size fits all’ approaches, as well as provide a route to formalizing a common practice of using ad hoc approaches when deciding or updating management plans. Here, we provide an introduction to adaptive treatment strategies, explaining their background, their purpose, and how they can be employed in practice. Copyright © 2014 John Wiley & Sons, Ltd.     

Validity and power considerations on hypothesis testing under minimization

Minimization, a dynamic allocation method, is gaining popularity especially in cancer clinical trials. Aiming to achieve balance on all important prognostic factors simultaneously, this procedure can lead to a substantial reduction in covariate imbalance compared with conventional randomization in small clinical trials. While minimization has generated enthusiasm, some controversy exists over the proper analysis of such a trial. Critics argue that standard testing methods that do not account for the dynamic allocation algorithm can lead to invalid statistical inference. Acknowledging this limitation, the International Conference on Harmonization E9 guideline suggests that ‘the complexity of the logistics and potential impact on analyses be carefully evaluated when considering dynamic allocation’. In this article, we investigate the proper analysis approaches to inference in a minimization design for both continuous and time‐to‐event endpoints and evaluate the validity and power of these approaches under a variety of scenarios both theoretically and empirically. Published 2016. This article is a U.S. Government work and is in the public domain in the USA     

Estimation of a common odds ratio in paired-cluster randomization designs

We develop two estimators of a common odds ratio psi for designs in which the investigator randomly assigns each of two clusters to interventions within strata. The estimators rely on an empirical adjustment for clustering to provide improved estimators of psi relative to the standard Woolf and Mantel-Haenszel estimators, respectively. The results of a simulation study show that the suggested adjustment improves the accuracy of both of these well-known estimators under conditions likely to arise in practice. We find the clustered Woolf estimator as particularly effective in terms of mean squared error reduction. We also discuss interval estimation.     

精神卫生科研如何严格遵守试验设计四原则之随机原则

明确阐释在进行精神卫生临床试验设计时,应正确把握"随机原则"的意义和要领。从基本常识出发,并基于精神卫生科研的特点,寻找和发现在此研究领域中,怎样做才能被称为严格遵守了"随机原则"。通过结合本专业的特点,并结合实例,获得如下的结果,即在进行精神卫生临床试验设计时,必须把握好以下三个方面:1正确选定随机化的种类;2正确方便地实现随机化;3必须尽可能避免违背随机化的做法。在如何严格遵守随机原则问题上,正确把握好前述提及的三个方面,就是抓住了问题的本质,是提高临床试验研究质量的一个重要环节。     

Sample size considerations for stratified cluster randomization design with binary outcomes and varying cluster size

Stratified cluster randomization trials (CRTs) have been frequently employed in clinical and healthcare research. Comparing with simple randomized CRTs, stratified CRTs reduce the imbalance of baseline prognostic factors among different intervention groups. Due to the popularity, there has been a growing interest in methodological development on sample size estimation and power analysis for stratified CRTs; however, existing work mostly assumes equal cluster size within each stratum and uses multilevel models. Clusters are often naturally formed with random sizes in CRTs. With varying cluster size, commonly used ad hoc approaches ignore the variability in cluster size, which may underestimate (overestimate) the required number of clusters for each group per stratum and lead to underpowered (overpowered) clinical trials. We propose closed-form sample size formulas for estimating the required total number of subjects and for estimating the number of clusters for each group per stratum, based on Cochran-Mantel-Haenszel statistic for stratified cluster randomization design with binary outcomes, accounting for both clustering and varying cluster size. We investigate the impact of various design parameters on the relative change in the required number of clusters for each group per stratum due to varying cluster size. Simulation studies are conducted to evaluate the finite-sample performance of the proposed sample size method. A real application example of a pragmatic stratified CRT of a triad of chronic kidney disease, diabetes, and hypertension is presented for illustration.