U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

EVALUATING HUMAN SERVICE AND CRIMINAL JUSTICE PROGRAMS BY MODELING THE PROBABILITY AND TIMING OF RECIDIVISM

NCJ Number
54099
Author(s)
H S BLOOM
Date Published
1978
Length
31 pages
Annotation
A METHOD FOR DETERMINING THE SHORT-TERM AND LONG-TERM IMPACT OF PROGRAMS AIMED AT REDUCING RECIDIVISM AMONG OFFENDERS, DRUG ABUSERS, AND ALCOHOLICS IS PRESENTED.
Abstract
THE PROPOSED METHOD PROVIDES EVALUATORS WITH THREE CAPABILITIES: EXAMINATIONS OF SHORT-TERM PROGRAM IMPACTS ON THE POSTPONEMENT OF RECIDIVISM THROUGH ESTIMATES OF THE AVERAGE TIME AT WHICH RECIDIVISM OCCURS, MEASUREMENT OF LONG-TERM IMPACT ON PREVENTION OF RECIDIVISM THROUGH ESTIMATES OF THE ULTIMATE PROBABILITY OF RECIDIVISM, AND DETERMINATION OF WHETHER INDIVIDUALS HAVE BEEN SUCCESSFUL LONG ENOUGH TO BE CONSIDERED 'SAFE' THROUGH ESTIMATES OF THEIR CONDITIONAL PROBABILITY OF FUTURE RECIDIVISM. THE STATISTICAL MODEL UNDERLYING THE METHOD IS BASED ON THE PREMISE THAT THE LONGER SOMEONE IS SUCCESSFUL (I.E., AVOIDS RECIDIVISM) THE MORE LIKELY HE OR SHE IS TO REMAIN SUCCESSFUL. THIS PREMISE DIFFERS FROM THAT OF AN EARILER MODEL, WHICH ASSUMED THAT AN INDIVIDUAL'S ULTIMATE SUCCESS OR FAILURE IS DETERMINED COMPLETELY UPON RELEASE. THE DERIVATION AND POLICY PARAMETERS OF THE PROPOSED MODEL ARE DESCRIBED. APPLICATION OF THE MODEL TO PROGRAM FOLLOWUP DATA IS EXPLAINED AND ILLUSTRATED IN AN EXAMPLE EMPLOYING FOLLOWUP DATA ON 257 ILLINOIS PAROLEES. A COMPARISON OF THE RESULTS OBTAINED BY APPLYING THE PROPOSED MODEL AND THE EARLIER MODEL MENTIONED ABOVE TO THE SAME DATA REVEALS THAT THE TWO MODELS YIELD SIMILAR POLICY IMPLICATIONS. IT IS NOTED, HOWEVER, THAT THE PROPOSED MODEL, BECAUSE ITS BASIC ASSUMPTIONS ARE MORE PLAUSIBLE, IS LIKELY TO FIND GREATER ACCEPTANCE IN THE POLICY DETERMINATION PROCESS. DIRECTIONS FOR FURTHER DEVELOPMENT OF THE PROPOSED MODEL ARE SUGGESTED. SUPPORTING DATA AND MATHEMATICAL FORMULATIONS ACCOMPANY THE TEXT, MUCH OF WHICH IS COUCHED IN STATISTICAL TERMINOLOGY.