I recently read an article "Remdesivir in adults with severe COVID-19: a randomised, double-blind, placebo-controlled, multicentre trial" (https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(20)31022-9/fulltext ). This is an RCT, and the authors have assigned participants to the intervention group and placebo group in the ratio 2:1. While there is evidence that statistical power increases as allocation ratio changes from 1:1 to 1:4, I couldn't find any literature on what happens to the power as the number of controls decrease compared to intervention arm. STATA does not allow to look for the same. Does the power decrease when this is done? What are the considerations which have to be taken into account while interpreting such results when no significant difference is seen?

More Vignesh Dwarakanathan's questions See All
Similar questions and discussions