%0 Journal Article
%T 美国州内与州际阿片危机预测模型——基于马尔可夫链模型的预测分析<br> US Intrastate and Interstate Opioid Crisis Prediction Model—Predictive Analysis Based on Markov Chain Model
%A 李碧璇
%A 朱可馨
%A 陈宣霖
%A 王访
%J Statistics and Applications
%P 394-403
%@ 2325-226X
%D 2019
%I Hans Publishing
%R 10.12677/SA.2019.82044
%X <div style=\"text-align:justify;\">
	<span style=\"font-size:14px;\">本文选取美国肯塔基州、俄亥俄州、宾夕法尼亚州、弗吉尼亚州和西弗吉尼亚州从2010年到2017年的县内阿片类药物鉴定数与州内阿片类药物鉴定数作为研究对象，并对该数据进行可视化分析，初步确定阿片类药物的大致转移趋势，结果显示阿片类药物主要集中在州的边境。然后利用关联度分析，以主要的阿片类药物海洛因作为参考标准，选取了海洛因、羟考酮、芬太尼、氢可待因和丁丙诺啡5种阿片类药物来衡量阿片类药物总体的使用情况。运用马尔可夫链模型，对美国5个州内阿片类药物的使用情况进行预测，给出5种阿片类药物数量的阈值水平，供美国政府参考。结果显示，美国政府需要加大力度对芬太尼药物进行控制，在西弗吉尼亚州的阿片类药物的使用情况相对最佳。<br />
This article analyzes the annul use of synthetic opioids at the state
and county levels in Kentucky, Ohio, Pennsylvania, Virginia, and West Virginia
during the year 2010-2017. After carrying out the visual analysis of the data,
the general transfer trend of two target substances can be initially determined,
and the results show that the use of target substances is more serious at
cities on the border. Then, we select the use of heroin as the reference
sequence and make oxycodone, fentanyl, hydrocodeine and buprenorphine represent
the other synthetic opioids according to the results of correlation analysis.
Using the Markov chain model, the use of the target substances in five studied
states can be predicted, and the threshold level of the number of opioids in
five states is given as reference for the governors. The results show that the
US government needs to concentrate more on the control of fentanyl drugs, and
the use of opioids in West Virginia is relatively optimal.</span> 
</div>
%K 阿片危机，关联度分析，马尔可夫链预测模型，蒙特卡罗算法<br> Opioid Crisis
%K Correlation Analysis
%K Markov Chain Prediction Model
%K Monte Carlo Algorithm
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=29917