Validity and power of minimization algorithm in longitudinal analysis of clinical trials

Weng, Hua; Bateman, Randall J.; Morris, John C.; Xiong, Chengjie

doi:10.1080/24709360.2017.1331822

Cited by 7 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most notably, the unadjusted t-test has been theoretically demonstrated to be conservative for a variety of covariate-adaptive designs, including the stratified permuted block design and Pocock and Simon's minimization method (Ma et al, 2015;Shao et al, 2010). Unadjusted testing was also found to be conservative in longitudinal analysis of clinical trials (Weng et al, 2017). See Bugni et al (2018), Ma et al (2020), andMa et al (2020) for the most recent work concerning more general model assumptions and randomization methods.…”

Section: Introductionmentioning

confidence: 99%

Testing for treatment effect in covariate-adaptive randomized trials with generalized linear models and omitted covariates

Qin

et al. 2021

Stat Methods Med Res

View full text Add to dashboard Cite

Concerns have been expressed over the validity of statistical inference under covariate-adaptive randomization despite the extensive use in clinical trials. In the literature, the inferential properties under covariate-adaptive randomization have been mainly studied for continuous responses; in particular, it is well known that the usual two-sample t-test for treatment effect is typically conservative. This phenomenon of invalid tests has also been found for generalized linear models without adjusting for the covariates and are sometimes more worrisome due to inflated Type I error. The purpose of this study is to examine the unadjusted test for treatment effect under generalized linear models and covariate-adaptive randomization. For a large class of covariate-adaptive randomization methods, we obtain the asymptotic distribution of the test statistic under the null hypothesis and derive the conditions under which the test is conservative, valid, or anti-conservative. Several commonly used generalized linear models, such as logistic regression and Poisson regression, are discussed in detail. An adjustment method is also proposed to achieve a valid size based on the asymptotic results. Numerical studies confirm the theoretical findings and demonstrate the effectiveness of the proposed adjustment method.

show abstract

Section: Introductionmentioning

confidence: 99%

Testing for treatment effect in covariate-adaptive randomized trials with generalized linear models and omitted covariates

Qin

et al. 2021

Stat Methods Med Res

View full text Add to dashboard Cite

show abstract

“…First, participant allocation should result in balanced sample sizes across study conditions to maximize statistical power. [7][8][9] Second, participant allocation should result in study conditions that are equivalent with respect to covariates that are expected to impact intervention outcomes (i.e., equivalent groups; 10 ). Third, participant allocation should be completely unpredictable to both study staff and to participants so as to ensure that measured and unmeasured participant characteristics, and selection biases in general, do not influence participants' assignment to conditions.…”

Section: Introductionmentioning

confidence: 99%

Simulation and minimization: Technical advances for factorial experiments designed to optimize clinical interventions

Kuhn

Sheldrick

Broder‐Fingert

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: The Multiphase Optimization Strategy (MOST) is designed to maximize the impact of clinical healthcare interventions, which are typically multicomponent and increasingly complex. MOST often relies on factorial experiments to identify which components of an intervention are most effective, efficient, and scalable. When assigning participants to conditions in factorial experiments, researchers must be careful to select the assignment procedure that will result in balanced sample sizes and equivalence of covariates across conditions while maintaining unpredictability. Methods: In the context of a MOST optimization trial with a 2x2x2x2 factorial design, we used computer simulation to empirically test five subject allocation procedures: simple randomization, stratified randomization with permuted blocks, maximum tolerated imbalance (MTI), minimal sufficient balance (MSB), and minimization. We compared these methods across the 16 study cells with respect to sample size balance, equivalence on key covariates, and unpredictability. Leveraging an existing dataset to compare these procedures, we conducted 250 computerized simulations using bootstrap samples of 304 participants. Results: Simple randomization, the most unpredictable procedure, generated poor sample balance and equivalence of covariates across the 16 study cells. Stratified randomization with permuted blocks performed well on stratified variables but resulted in poor equivalence on other covariates and poor balance. MTI, MSB, and minimization had higher complexity and cost. MTI resulted in balance close to pre-specified thresholds and a higher degree of unpredictability, but poor equivalence of covariates. MSB had 19.7% deterministic allocations, poor sample balance and improved equivalence on only a few covariates. Minimization was most successful in achieving balanced sample sizes and equivalence across a large number of covariates, but resulted in 34% deterministic allocations. Small differences in proportion of correct guesses were found across the procedures. Conclusions: Based on the computer simulation results and priorities within the study context, minimization with a random element was selected for the planned research study. Minimization with a random element, as well as computer simulation to make an informed randomization procedure choice, are utilized infrequently in randomized experiments but represent important technical advances that researchers implementing multi-arm and factorial studies should consider.

show abstract

“…Consensus guidelines for reporting randomized trials (i.e., Consolidated Standards of Reporting Trials (CONSORT); [7]) describe a range of acceptable methods for allocation of participants to study cells and suggest that three criteria are important for determining which method to use. First, participant allocation should result in balanced sample sizes across study conditions to maximize statistical power [7,8,9]. Second, participant allocation should result in study conditions that are equivalent with respect to covariates that are expected to impact intervention outcomes (i.e., equivalent groups; [10]).…”

Section: Introductionmentioning

confidence: 99%

Simulation and minimization: Technical advances for factorial experiments designed to optimize clinical interventions

Kuhn

Sheldrick

Broder‐Fingert

et al. 2019

Preprint

View full text Add to dashboard Cite

Background The Multiphase Optimization Strategy (MOST) is designed to maximize the impact of clinical healthcare interventions, which are typically multicomponent and increasingly complex. The MOST framework often relies on factorial experiments to identify which components of an intervention are most effective, efficient, and scalable. When assigning participants to conditions in factorial experiments, researchers must be careful to select the assignment method that will result in balanced sample sizes and equivalence of covariates across conditions without being predictable. Historically, procedures most often include simple randomization and stratification with blocking; minimization is an increasingly utilized method that assigns participants to the condition that minimizes differences in covariates and sample size across study conditions. Methods In the context of a MOST optimization trial with a 2x2x2x2 factorial design (4 components, 16 cells), we used computer simulation to empirically test three subject assignment methods: simple randomization, stratification with blocking, and minimization. We compared these methods with respect to: sample size balance across condition, equivalence across conditions on key covariates, and unpredictability of assignments. Leveraging an existing dataset to compare three different allocation methods, we conducted 250 computerized simulations using bootstrap samples of 304 participants, which was the planned sample size for the proposed study. Result Simple randomization, the most unpredictable subject allocation method, generated the least balance of sample and equivalence of covariates across the 16 study cells. Stratification with blocking performed well on stratified variables, and resulted in similar sample balance and predictability as minimization. In contrast, minimization, which had a higher degree of complexity and cost, was most successful in achieving balanced sample sizes and equivalence across a large number of covariates. Conclusions Unlike simple randomization, minimization procedures and stratification with blocking are both methodologically sound options for factorial designs. Based on the computer simulation results and priorities within context of this MOST optimization trial, minimization was selected as the optimal subject allocation method. Minimization is utilized infrequently in randomized experiments but represents an important technical advance that should be considered by researchers implementing multi-arm and factorial studies.

show abstract

Validity and power of minimization algorithm in longitudinal analysis of clinical trials

Cited by 7 publications

References 24 publications

Testing for treatment effect in covariate-adaptive randomized trials with generalized linear models and omitted covariates

Testing for treatment effect in covariate-adaptive randomized trials with generalized linear models and omitted covariates

Simulation and minimization: Technical advances for factorial experiments designed to optimize clinical interventions

Simulation and minimization: Technical advances for factorial experiments designed to optimize clinical interventions

Contact Info

Product

Resources

About