To the Editor A well-defined exposure is essential for a cohort study to determine an association between the exposure and a specific outcome. A lower-dose exposure is only useful and statistically powerful when used to examine a dose-response relationship; used only as a control, it is likely to underestimate an association. An infamous example of misclassification of exposed and nonexposed groups and a subsequent null result was the Danish study assessing risk of brain tumors from mobile phones.1
Fernandes GS, Doherty M, Zhang W. Professional Football Participation and Mortality. JAMA. 2018;320(1):91–92. doi:10.1001/jama.2018.6705
Browse and subscribe to JAMA Network podcasts!
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: