Site-variable allocation ratios in randomized controlled trials: implications for sample size, recruitment efficiency, and statistical analysis
Bibliographic record
Abstract
ABSTRACT Introduction In multicentre randomized trials, some sites face logistical constraints that specifically affect their ability to recruit into one arm of the trial more than other arms. Often these are greater limits on their ability to deliver one of the study interventions. This paper proposes the use of allocation ratios that differ by site to increase recruitment capacity in asymmetrically constrained sites. Methods Simulations of randomized trials assessed the impact of several allocation ratios (1:1 to 1:5)—and variation of ratios across sites—on sample size and recruitment capacity, and evaluated several adjustment approaches for time-to-event, binary, and continuous outcomes to prevent bias from site-variable allocation ratios. Results Deviating from 1:1 allocation increases recruitment capacity within sites facing asymmetric constraints faster than it increases sample size requirements. For instance, a 1:3 ratio increased sample size by 35% but doubled the hypothetical recruitment capacity with fewer sites. The bias in treatment effect estimates that occurs when the baseline risk or outcome mean differ between sites allocated with different ratios was readily prevented with simple covariate adjustment or stratification by site or allocation ratio. Conclusions Site-variable allocation ratios may relieve recruitment bottlenecks caused by asymmetric constraints in trial procedures that affect some of the sites in a trial. Accounting for the variation in allocation ratios during analysis is necessary to ensure unbiased treatment effect estimates. This strategy is particularly relevant for trials with low marginal costs for participant recruitment and follow-up, such as many large pragmatic trials embedded in routine care.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.550 | 0.785 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.005 | 0.005 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.008 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.005 | 0.004 |
| Research integrity | 0.007 | 0.009 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".