To the Editor A Research Letter recently published in JAMA Internal Medicine by Hadland and colleagues1 reported on the relationship between pharmaceutical industry marketing of opioid products to physicians in 2014 and the frequency of opioid prescriptions by physicians in 2015. The authors carried out a difference-in-differences analysis to show that among physicians who prescribed opioids in 2015, those who received payments involving opioid products in 2014 had higher opioid prescribing levels in 2015. Hadland and colleagues are forthright in noting that the findings “establish an association, not cause and effect.”1(p863) While this correlation undoubtedly exists, the authors then concluded that these results support policy changes that only make sense if this correlation also represents a causal link that flows from payments to opioid prescriptions. In particular, Hadland and colleagues recommended “a voluntary decrease or complete cessation of marketing to physicians”1(p863) by manufacturers, as well as consideration of “legal limits on the number and amount of payments” by federal and state governments. If the implied causal link does not exist, these measures would merely limit the information and other resources available to physicians without reducing unwarranted opioid prescriptions.