Working Paper: NBER ID: w2445
Authors: Peter Schmidt; Ann Dryden Witte
Abstract: In this paper we develop a survival time model in which the probability of eventual failure is less than one, and in which both the probability of eventual failure and the timing of failure depend (separately) on individual characteristics. We apply this model to data on the tiring of return to prison for a sample of prison releasees, and we use it to make predictions of whether or not individuals return to prison. Our predictions are more accurate than previous predictions of criminal recidivism. The model we develop has potential applications in economics: far example, it could tie used to model the probability of default and the timing of default on loans.
Keywords: recidivism; survival models; criminal justice; econometrics
JEL Codes: C41; K14
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| race (J15) | probability of eventual recidivism (C41) |
| sex (J16) | probability of eventual recidivism (C41) |
| specific indicators of prior offenses (K42) | timing of recidivism (C41) |
| probability of eventual recidivism (C41) | recidivism (K14) |