Assessing Ecstasy Risk in Kaohsiung City: A Zero-Inflated Poisson Model Approach with Spatiotemporal Analysis
- 2024-05-13 (Mon.), 10:30 AM
- 統計所B1演講廳;茶 會:上午10:10。
- 中文演講,實體與線上視訊同步進行。
- Prof. Hong-Ding Yang ( 楊洪鼎 助理教授 )
- 國立嘉義大學應用數學系
Abstract
This study explores the application of the zero-inflated Poisson model for analyzing ecstasy incidents in Kaohsiung City, incorporating the spatiotemporal correlation of data. We introduce a risk assessment method within the Bayesian hierarchical model framework, preceded by selecting explanatory variables based on the Deviance Information Criterion (DIC). Additionally, quantile regression is incorporated into the model to understand data distribution under different percentiles. Markov Chain Monte Carlo (MCMC) methods generate essential parameters and random effect terms, establishing a risk assessment criterion for ecstasy incidents. Furthermore, this method is compared with alternative approaches to evaluate its effectiveness. Based on the ecstasy data, the proposed methodology provides a refined understanding of the spatiotemporal distribution of ecstasy incidents and introduces a risk assessment tool
for relevant authorities.最後更新日期:2024-04-19 16:00