摘要
循环效应模型可以用于研究两变量间的双向互动关系,网络效应模型可以用于探讨关系网络对个体行为的影响,但目前能同时研究循环效应和网络效应的模型还未发现。基于此,文章综合考虑两类模型的效应,构建了动态循环网络效应模型,给出了模型可识别条件和贝叶斯估计方法,并分别运用网络效应模型、循环效应模型和新构建模型对空气污染问题进行实证分析。结果表明,与其他两类模型相比,新模型的研究结果更加全面,同时也验证了新模型的可行性和有效性。
Cyclic effect model can be used to study the two-way interaction between two variables,and network effect model can be used to explore the influence of relationship network on individual behavior.However,no model has been found yet that can study the cyclic effect and network effect at the same time.In view of this,the paper constructs a dynamic cyclic network effect model by comprehensively considering the effects of the two models,and gives the recognition conditions and Bayesian estimation method of the model.Finally,the paper uses the network effect model,cyclic effect model and newly constructed model to conduct an empirical analysis on the air pollution problem respectively.The results show that the new model is more comprehensive than the other two models.The feasibility and validity of the new model are also verified.
作者
王传美
张炼
孙浩艺
Wang Chuanmei;Zhang Lian;Sun Haoyi(School of Mathematics and Statistics,Wuhan University of Technology,Wuhan 430070,China)
出处
《统计与决策》
CSSCI
北大核心
2021年第12期33-37,共5页
Statistics & Decision
基金
中央高校基本科研业务费专项资金资助项目(2018IB016
2019IA004
2019-LX-B1-07)。
关键词
动态循环
网络效应
模型识别
贝叶斯估计
空气污染
dynamic cycle
network effect
model recognition
Bayesian estimation
air pollution
