Assessing Evidence vs. Truth in the Coronavirus Pandemic

ABSTRACT

Gelman offers insights about evidence versus truth in the coronavirus pandemic. Coronavirus tests were hard to come by at that time, and everyone knew that the number of confirmed cases was much lower than the total number of people exposed, but it was not clear how much lower. The Stanford study was posted on the preprint server medRxiv on April 11, and its authors were soon writing op-eds and explaining the implications of their findings on national television. The key result from their preprint was a range of estimates of 2.5% to 4.2% for the prevalence rate, implying between 48,000 and 81,000 people infected in Santa Clara County by early April, 50-85-fold more than the number of confirmed cases.