暴力风险评估中的统计预测方法及其应用

摘要

如何改进暴力风险评估是一个亟待解决的全球性难题,通过统计学方法进行犯罪的暴力风险评估是其中不可或缺的一环,作用十分重要.本文主要从统计学角度对暴力风险评估预测方法进行了回顾,并对其中较为常用的多元统计模型代表的Logistic回归模型、数据挖掘技术代表的决策树模型以及人工智能技术代表的神经网络模型及其应用进行综述,以期为暴力风险评估的进一步研究提供参考.%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.