cluster randomized trial
A randomized experiment in which whole groups (e.g., villages or municipalities) rather than individuals are assigned to intervention or control arms.
As defined in Vinay Prasad on the Pandemic
Where it comes up · 2
- Vinay Prasad on the Pandemic2 claims
- The Good, the Bad, and the Ugly of the Covid Vaccine (with Vinay Prasad)1 claim
Most important claims · 3 of 3Search all claims for “cluster randomized trial” →
- Abaluck's Bangladesh cluster RCT found only an 11% relative risk reduction (0.76% to 0.69% absolute, a tiny effect) limited to surgical masks—cloth masks did not work—and the result is questionable due to a statistically significant 10% randomization imbalance from concealment bias (people signing up for the free mask).Vinay Prasad on the Pandemic
- Despite being an imminently answerable question, the UK, US, and indeed no nation ran cluster randomized trials of cloth community masking, and no one ran any in children—least of all in the most-disputed group of two-to-five-year-olds—leaving the issue evidence-free.Vinay Prasad on the Pandemic
- Pre-pandemic randomized studies of community masking were generally negative, and the three pandemic-era randomized trials (Guinea-Bissau, Bangladesh, Denmark/DanMask) plus the new Cochrane Review remain negative or inconclusive; governments failed to run cluster-randomized trials to determine whether community masking, especially in young children, actually worked, partly because the question became too politically polarized to study.The Good, the Bad, and the Ugly of the Covid Vaccine (with Vinay Prasad)