摘要
每日新增确诊病例和每日新增无症状感染者病例在探索新冠疫情的传播模式,分析疫情传播的影响因素等方面起着关键作用,因此利用合理的统计方法来探究它们的分布特征具有很重要的理论与实际意义.文中根据新疆乌鲁木齐市新冠疫情每日新增确诊病例与每日新增无症状感染者病例的实际数据,以探究数据的分布特征为目的,分别基于泊松分布,变点泊松分布与过度发散泊松分布对数据进行统计建模,利用贝叶斯方法对模型进行统计推断,并利用DIC值来评价各个模型的优劣.结果表明,三种模型对实际样本数据具有一定的的合理性,相比之下,基于过度发散泊松分布的模型具有最高的拟合优度,其次为变点泊松模型,泊松模型的拟合优度相对较差.
The daily new confirmed cases and daily asymptomatic cases play a key role in exploring the transmission patterns of the COVID-19 and analyzing the influencing factors of the epidemic transmission.Therefore,it is of great theoretical and practical significance to explore their distribution characteristics by using reasonable statistical methods.In this paper based on actual data of the daily new confirmed cases and daily asymptomatic cases of COVID-19 in Urumqi,Xinjiang,for the purpose of exploring the distribution characteristics of the data,establish statistical models based on poisson distribution,change-point poisson distribution and overdispersion poisson distribution respectively.The Bayesian method is used to statistical inference for the model parameters,and through the DIC values evaluate the advantages and disadvantages of each model.The results showed that the three models are reasonable.By comparison,the model based on overdispersion poisson distribution has the highest goodness of fit,followed by the change point poisson model,and the goodness of fit of poisson model is relatively poor.
作者
古丽斯坦·库尔班尼牙孜
田茂再
GULISTAN Kuerbanyaz;TIAN Mao-zai(School of Statistics and data Science,Xinjiang University of Finance and Economics,Urumqi 830012,China;Center for Applied Statistics,School of Statistics,Renmin University of China,Beijing 100872,China)
出处
《高校应用数学学报（A辑）》
北大核心
2022年第2期226-236,共11页
Applied Mathematics A Journal of Chinese Universities(Ser.A)
基金
国家自然科学基金(11861042)
国家自然科学基金(71864034)
新疆财经大学科研研究基金(2017XYB017)。
