Genetics and Crime: Integrating New Genomic Discoveries Into Psychological Research About Antisocial Behavior

Abstract

Drawing on psychological and sociological theories of crime causation, we tested the hypothesis that genetic risk for low educational attainment (assessed via a genome-wide polygenic score) is associated with criminal offending. We further tested hypotheses of how polygenic risk relates to the development of antisocial behavior from childhood through adulthood. Across the Dunedin and Environmental Risk (E-Risk) birth cohorts of individuals growing up 20 years and 20,000 kilometers apart, education polygenic scores predicted risk of a criminal record with modest effects. Polygenic risk manifested during primary schooling in lower cognitive abilities, lower self-control, academic difficulties, and truancy, and it was associated with a life-course-persistent pattern of antisocial behavior that onsets in childhood and persists into adulthood. Crime is central in the nature-nurture debate, and findings reported here demonstrate how molecular-genetic discoveries can be incorporated into established theories of antisocial behavior. They also suggest that improving school experiences might prevent genetic influences on crime from unfolding.

Keywords: antisocial behavior; crime; genetics; longitudinal.

Fig. 1.

Study timelines of the Environmental Risk (E-Risk) and Dunedin cohorts. The figure depicts the observation period of early-emerging psychological and behavioral risk factors (low cognitive ability, low self-control, academic difficulties in primary school, and truancy), school-leaving qualifications, and crime records (cautions and convictions) in the two cohorts and developmental trajectories of antisocial behavior in the Dunedin cohort.

Fig. 2.

Mean education polygenic score among participants with and without a criminal record, through age 19 years in the Environmental Risk (E-Risk) cohort and age 38 years in the Dunedin cohort. Error bars reflect standard errors, with robust standard errors in the E-Risk cohort. E-Risk and Dunedin participants with a criminal record had lower polygenic scores for education than participants without a criminal record.

Fig. 3.

Cumulative distribution of the first appearance in police records of cautions and convictions, by age, of the 196 participants with criminal records in the Environmental Risk (E-Risk) cohort. In the United Kingdom, compulsory schooling ends at age 16 years. The majority of E-Risk participants with criminal records received their first caution or conviction before school-leaving age.

Fig. 4.

Association between polygenic score for education and the timing and persistence of antisocial behavior across the life course. Panel (a) depicts the proportion of Dunedin participants with convictions by age (Kaplan Meier failure functions) among participants with low (< 1 SD below the mean) and high (> 1 SD above the mean) polygenic scores for educational attainment. Shaded areas show 95% confidence intervals. Panel (b) shows mean differences in polygenic score across four developmental subtypes of antisocial behavior in the Dunedin cohort, following Moffitt (1993b). Error bars reflect standard errors.