Statistical prediction methods in violence risk assessment and its application / 法医学杂志
Journal of Forensic Medicine
; (6): 216-221, 2013.
Article
en Zh
| WPRIM
| ID: wpr-983826
Biblioteca responsable:
WPRO
ABSTRACT
It is an urgent global problem how to improve the violence risk assessment. As a necessary part of risk assessment, statistical methods have remarkable impacts and effects. In this study, the predicted methods in violence risk assessment from the point of statistics are reviewed. The application of Logistic regression as the sample of multivariate statistical model, decision tree model as the sample of data mining technique, and neural networks model as the sample of artificial intelligence technology are all reviewed. This study provides data in order to contribute the further research of violence risk assessment.
Texto completo:
1
Base de datos:
WPRIM
Asunto principal:
Violencia
/
Psiquiatría Forense
/
Inteligencia Artificial
/
Árboles de Decisión
/
Modelos Logísticos
/
Valor Predictivo de las Pruebas
/
Estudios Retrospectivos
/
Factores de Riesgo
/
Redes Neurales de la Computación
/
Medición de Riesgo
Límite:
Humans
Idioma:
Zh
Revista:
Journal of Forensic Medicine
Año:
2013
Tipo del documento:
Article