Principal Investigator(s): Gottfredson, Stephen D., Justice Policy Research Corporation; Gottfredson, Don M., Justice Policy Research Corporation
These data were gathered to investigate the usefulness of statistical methods, particularly multiple-regression analysis, in predicting repeat criminal activity subsequent to an individual's release from prison. The data collection consists of follow-up information, collected in 1988, on a sample of males released from California prisons. The follow-up study identified criminal activity subsequent to individuals' release from prison through 1988. Predictor variables include age, prior periods of arrest, history of drug use, seriousness of original offense, and number of arrests for nuisance, person, property, and fraud offenses.
These data are freely available.
Gottfredson, Stephen D., and Don M. Gottfredson. CRIMINAL VIOLENCE AND INCAPACITATION IN CALIFORNIA, 1962-1988. Indianapolis, IN: Justice Policy Research Corporation [producer], 1991. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 1993. http://doi.org/10.3886/ICPSR09922.v1
Persistent URL: http://doi.org/10.3886/ICPSR09922.v1
This study was funded by:
- United States Department of Justice. Office of Justice Programs. National Institute of Justice (88-IJ-CX-0002)
Scope of Study
Unit of Observation: Individuals
Universe: Adult men released from California prisons between 1962 and 1988.
Data Types: event/transaction data
Study Purpose: The Justice Policy Research Corporation conducted this study to examine the extent to which statistical models are useful in predicting the likelihood of repeat criminal activity after release from prison. The sample was chosen in the early 1960s and was intended to be representative of all men in California prisons at that time. A follow-up study was done to identify criminal activity subsequent to individuals' release from prison through 1988. The follow-up study contains data on 4,897 men.
Study Design: The original sample, selected in the early 1960s, contained more than 6,000 individuals. The follow-up study attempted to include all individuals contained in the original sample. However, the California Bureau of Criminal Statistics and the California Bureau of Criminal Investigation were not able to provide records for all individuals, and attrition occurred for a variety of reasons. No records were provided for some individuals who had died. In some instances the individual was not released from prison. Some records were unusable (e.g., missing pages). A number of records were "purged" from the California system if the individual had reached age 70 and there were no known arrests in the prior ten years. These sources of attrition resulted in a follow-up sample of 4,897 individuals. Attrition may result in some sample bias. All deaths of individuals from the original sample may not be recorded, and unrecorded deaths may inflate the amount of time free without arrest. Complete records of out-of-state arrests were not available, and this may also inflate time without arrest. Purging of records should counteract the effects of unrecorded deaths and out-of-state arrests, since those remaining in the sample would tend to have had more arrests. The researchers compared characteristics of purged and retained cases and concluded that there appears to be little serious bias associated with sample attrition.
Sample: The original sample was chosen to be representative of men in California prisons in the early 1960s. The follow-up sample is the original sample less those cases lost due to attrition.
The California Bureau of Criminal Statistics and the California Bureau of Criminal Identification
Description of Variables: Data gathered for predictor variables include age of the individual, prior periods of arrest, history of drug use, type of offense, and seriousness of offense. Data regarding criminal activity subsequent to release from prison include number of arrests for nuisance offenses, person offenses, property offenses, and fraud offenses.
Response Rates: There are 4,897 members in the follow-up study representing 78 percent of the 6,310 members in the original sample.
Presence of Common Scales: None
Extent of Processing: ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:
- Checked for undocumented or out-of-range codes.
Original ICPSR Release: 1993-10-02
- 2005-11-04 On 2005-03-14 new files were added to one or more datasets. These files included additional setup files as well as one or more of the following: SAS program, SAS transport, SPSS portable, and Stata system files. The metadata record was revised 2005-11-04 to reflect these additions.
- Citations exports are provided above.
Export Study-level metadata (does not include variable-level metadata)