Differential response (DR) is a system reform that allows child protective services (CPS) agencies to divert low-to-moderate risk families from an investigative track to an alternate track that does not require a maltreatment disposition or identification of an alleged perpetrator. Knowledge of how DR alters the flow of cases through CPS systems has been restricted by methodological limitations in prior research. This study uses cross-sectional and longitudinal data from the National Child Abuse and Neglect Data System (NCANDS) child file to examine the extent to which DR implementation affects the number and demographic composition of cases investigated for neglect. Results from multivariate, multilevel cross-sectional analysis of 2010 data indicated that investigations were 2.4 times more likely to be substantiated in DR counties than in non-DR counties. Children with a previous substantiated report were also more likely to have a current report substantiated and this difference was significantly greater in DR counties than in non-DR counties. Child race and ethnicity did not predict substantiation decisions. Results from a mixed-effect longitudinal analysis of 997,512 cases from 269 counties between 2001 and 2010 suggest that the rate of investigations fell sharply nationwide within three years of DR implementation. However, substantiation rates did not change as a result of DR implementation. Instead, analysis indicated differences between DR and non-DR counties emerged before the launch of DR. The findings highlight the benefit of using “big data” and longitudinal analysis to assess large-scale policy changes.