Oleinick and Zaidman [2010] suggest that assumptions are a defect in empirical analysis. We interpret their argument to mean that we [Boden and Ozonoff, 2010]-and by implication others-should not rely on untested assumptions nor should we use sensitivity analyses ''to buttress results.'' Let us examine one assumption made in their response: that BLS reporting rates are the same for different types of cases ''since reporting rules are the same for all cases.'' This assumption is critical to their calculations, but we see no reason for it to be correct. For example, we suspect that reporting for an injury involving only 2 days off work is not as likely as for one involving 4 weeks off work. Indeed, a primary motivation for studying reporting is to see if reporting rules are being followed. If these rules are in fact not being followed, then the level of reporting may well depend on injury duration, injury type, conflict over benefit payments, and other factors.Empirical work, including ours and theirs, must rely on assumptions. Moreover, when a range of plausible assumptions cannot be tested in a particular study, it also seems appropriate to explore the sensitivity of results to alternate assumptions. Additional research can then be designed to determine whether such assumptions are warranted.