Randomized Safety Inspections and Risk Exposure on the Job: Quasi-Experimental Estimates of the Value of Statistical Life, Jonathan Lee and Laura Taylor, 2019, in the American Economic Journal--Economic Policy, right here: https://www.aeaweb.org/articles?id=10.1257/pol.20150024.
This recent article estimates the Value of Statistical Life (VSL) from randomized safety inspections conducted by OSHA (the U.S. department of Occupational Safety and Health), with conclusions that are typical of the literature. The article is fascinating nonetheless, with marvelous craftsmanship in several key respects, all undone by one major omission (and its corollaries). It is a great illustration of how fitting into the prevailing schema of "quasi-randomized experiments" does not ensure correct conclusions or make craftsmanship irrelevant! Place your thoughts in comments.