After hypothesizing that a state introduced a reform intended to reduce the use of incarceration for a targeted group of offenders, this paper discusses how data from the federal Bureau of Justice Statistics’ (BJS’) National Corrections Reporting Program (NCRP) might be used to examine what such a reform accomplished.
The rudiments of evaluation are discussed; however, formal designs are required to meet validity and reliability challenges to data and data analysis. Throughout this discussion, the evaluated reform is a state’s decision to reduce its prison population for the least serious offenders. This policy is implemented at a certain time, but it may be assumed that the intervention will take time to reach its full implementation, resulting in the full effect being lagged. This paper argues that interrupted time-series are poor designs that can lead to spurious findings, sometimes causing evaluators to reject interventions that are beneficial and sometimes causing evaluators to accept interventions that are ineffective. When the intervention targets a class of offenders, as in the hypothesized reduction of incarceration of less serious offenders, then a class of similar offenders within the same state may be a suitable “counterfactual;” i.e., what would happen if the change was not implemented during a given period. The NCRP is especially useful for studying recidivism, defined as returning to prison in the same state. The NCRP team is working on linking NCRP data across states. Questions about recidivism are equally amenable to the research designs posed in this paper. 8 figures, 5 tables