A common reason for not participating in intimate partner violence (IPV) research is thought to be fear for one's safety. However, little is known about those who do not participate due to safety fears. To better characterize this population, we investigated correlates of being "not safe" to answer the optional IPV module in the 2006 Behavioral Risk Factor Surveillance Survey (BRFSS), a yearly cross-sectional telephone survey in the United States. We compared those who said they were "not" safe to complete the module with those who were safe and reported (+IPV) or denied (-IPV) IPV. Forward stepwise multivariate logistic regression was performed to identify significant correlates of being not-safe. Those who said they were not safe to answer IPV questions were found to have lower income, lower education levels, and were older than either +IPV or -IPV respondents. They were also more likely to be male than the +IPV group. The not-safe differ from those traditionally identified as being at greatest risk for IPV. However, the percentage of IPV victims in the not-safe group remains unknown. Greater efforts should be made to include this group in future IPV research, both to determine these groups' true IPV risk and to avoid missing potential IPV victims. The validity, reliability, and comprehensibility of safety questions should also be assessed. (Contains 3 tables and 1 note.)