Search Results
Author: Oh, Gyeongseok
Resulting in 2 citations.
| 1. |
Oh, Gyeongseok |
|
Predicting Life-Course Persistent Offending Using Machine Learning Ph.D. Dissertation, Department of Criminal Justice and Criminology, Sam Houston State University, 2021 Cohort(s): NLSY97 Publisher: ProQuest Dissertations & Theses (PQDT) Keyword(s): Crime; Criminal Justice System; Life Course; Modeling, Latent Class Analysis/Latent Transition Analysis Permission to reprint the abstract has not been received from the publisher. The current study investigated the predictive ability of Life-Course-Persistent (LCP) offenders using Machine Learning techniques. Drawing on the National Longitudinal Survey of Youth 1997, LCP and adolescent limited offenders are identified by the latent class growth analysis. Using seven types of Machine Learning techniques, the LCP offenders are predicted by risk factors verified by previous empirical studies. The results of predictive modeling reveal that the Machine Learning-based prediction of LCP offenders significantly outperforms the conventional parametric statistical analysis, logistic regression. Most of all, the predictive ability of Random Forests and Deep Learning model show a more effective forecasting ability than other Machine Learning- based modeling and logistic regression analysis. |
|
|
Bibliography Citation
Oh, Gyeongseok. Predicting Life-Course Persistent Offending Using Machine Learning. Ph.D. Dissertation, Department of Criminal Justice and Criminology, Sam Houston State University, 2021. |
| 2. |
Oh, Gyeongseok Connolly, Eric J. |
|
The Role of Depressive Symptoms between Neighbourhood Disorder, Criminal Justice Contact, and Suicidal Ideation: Integrating an Ecological Stress Model with General Strain Theory Criminal Behaviour and Mental Health 32,1 (February 2022): 35-47. Also: https://onlinelibrary.wiley.com/doi/10.1002/cbm.2229 Cohort(s): NLSY79, NLSY79 Young Adult Publisher: Wiley Online Keyword(s): Alcohol Use; Criminal Justice System; Depression (see also CESD); Drug Use; General Strain Theory; Neighborhood Effects Permission to reprint the abstract has not been received from the publisher. Aims: Our aim was to examine whether depressive symptoms mediate association between perceived neighbourhood disorder, future criminal justice contact, and future suicidal ideation. Methods: We grounded this research in primary arguments derived from General Strain Theory (GST). Data were drawn from structured self-reports in surveys of over 2000 young adult participants from the Children of the National Longitudinal Survey of Youth, who are the offspring born to the women from the National Longitudinal Survey of Youth 1979. Information on neighbourhood disorder and depressive symptoms were used from the 2012 data collection period, while information on criminal justice contact and suicidal ideation were drawn from the 2014 period. Structural equation modelling was used to examine both direct and indirect pathways between neighbourhood disorder, depression, contact with the justice system, and suicidal ideation from 2012 to 2014. Results: Depressive symptoms were found to partially mediate the effect of perceived neighbourhood disorder on future criminal justice contact, with the strength of this effect varying across categories of race/ethnicity. The association between perceived neighbourhood disorder and suicidal ideation was fully mediated by depressive symptoms. |
|
|
Bibliography Citation
Oh, Gyeongseok and Eric J. Connolly. "The Role of Depressive Symptoms between Neighbourhood Disorder, Criminal Justice Contact, and Suicidal Ideation: Integrating an Ecological Stress Model with General Strain Theory." Criminal Behaviour and Mental Health 32,1 (February 2022): 35-47.
|