In reply
We thank the authors of the letter for their comments. Andersohn and Willich noted some methodological concerns with our analysis, particularly the potential “healthy adherer” bias. A recent study1 aimed to examine whether adherence with statin use is associated with a decreased risk of unintentional injuries that were sought to be unrelated to statins (eg, motor vehicle crashes and workplace injuries, burns, and falls). As expected, they found a modest (10%-15%) overall reduction in the rate of unintentional injuries among adherent patients compared with nonadherent ones. Thus, the “healthy adherer” bias could explain some of our results, but clearly not a 45% reduction in all-cause mortality.