Lancaster EPrints

Estimation issues and generational changes in modelling criminal career length

Francis, Brian J. and Piquero, Alex R. and Soothill, Keith (2007) Estimation issues and generational changes in modelling criminal career length. Crime & Delinquency, 53 (1). pp. 84-105.

Full text not available from this repository.

Abstract

This article seeks to model criminal career length using data from six different birth cohorts born between 1953 and 1978, totaling more than 58,000 males and females from England and Wales. A secondary aim of this article is to consider whether information available at the first court appearance leading to a conviction is associated with the length of a criminal career. Four key findings emerged. First, one can estimate career length from variables available at the first court conviction. Second, the risk of desistance remains constant during a period of 20 to 25 years if the offender does not immediately stop after the first conviction. Third, the most significant variable is age at first conviction. Finally, gender differences and birth cohorts are also important.

Item Type: Article
Journal or Publication Title: Crime & Delinquency
Additional Information: RAE_import_type : Journal article RAE_uoa_type : Statistics and Operational Research
Uncontrolled Keywords: career length • criminal careers • cohort effects • Cox model • survival analysis
Subjects: Q Science > QA Mathematics
Departments: Faculty of Science and Technology > Mathematics and Statistics
Faculty of Arts & Social Sciences > Applied Social Science
ID Code: 2468
Deposited By: ep_importer
Deposited On: 31 Mar 2008 11:20
Refereed?: Yes
Published?: Published
Last Modified: 09 Oct 2013 15:17
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/2468

Actions (login required)

View Item