Statistical prediction methods in violence risk assessment and its application.
- Author:
Yuan-Yuan LIU
1
;
Jun-Mei HU
;
Min YANG
;
Xiao-Song LI
Author Information
1. Department of Health Statistics, School of Public Health, Sichuan University, Chengdu 610041, China.
- Publication Type:Review
- MeSH:
Artificial Intelligence;
Decision Trees;
Forensic Psychiatry/methods*;
Humans;
Logistic Models;
Neural Networks, Computer;
Predictive Value of Tests;
Retrospective Studies;
Risk Assessment/statistics & numerical data*;
Risk Factors;
Violence/statistics & numerical data*
- From:
Journal of Forensic Medicine
2013;29(3):216-221
- CountryChina
- Language:Chinese
-
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.