This commentary is a critique of Impact of community masking on COVID-19: A cluster-randomized trial in Bangladesh:
"A recent randomized trial evaluated the impact of mask promotion on COVID-19-related outcomes. We find that staff behavior in both unblinded and supposedly blinded steps caused large and statistically significant imbalances in population sizes. These denominator differences constitute the rate differences observed in the trial, complicating inferences of causality...
The Bangladesh mask trial reported decreases in symptomatic seroprevalence (primary outcome), decreases in reported COVID-19-like symptoms (secondary outcome), and increases in mask wearing behavior (secondary outcome). The study analyzed the data with a generalized linear model and found a 10% decrease in the primary endpoint, evaluating this result as significant at p = 0.05.
In this commentary, we re-analyze this trial using simple non-parametric tests. Upon reanalysis, we find a large, statistically significant imbalance in the size of the treatment and control arms evincing substantial post-randomization ascertainment bias by unblinded staff. The observed decrease in the primary outcome is the same magnitude as the population imbalance but fails significance by the same tests...
Although raw numbers were not presented in the published paper, the primary outcome differed by a total of just 20 cases between the treatment and control arms: In a study population of over 300,000 individuals, there were 1106 symptomatic seropositives in control and 1086 in treatment. In particular, the difference in rates is constituted by denominator differences, and thus is similar in magnitude (10% vs 9%) to the population imbalance which arose through the interaction of staff bias and random chance (156,938 and 170,497 individuals enrolled in control and treatment respectively)."
© The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.