Chikina et al.: "Re-analysis on the statistical sampling biases of a mask promotion trial in Bangladesh: a statistical replication"; now saying with even the modest 'claimed' benefit, DO NOT trust

by Paul Alexander

Bottom line is that the re-analysis shows research methods that may likely have contributed to the finding and it was not even great, ranging from no (zero) benefit to a very small modest one

Background: this was based on a cluster randomized Bangladeshi study on the effectiveness of the COVID face masks, the researchers then reporting results ranging from no benefit to a small modest benefit. Now a re-analysis is suggesting the methods were problematic.