Analyzing the Dissemination of News by Model Averaging and Subsampling  

作　　者：ZOU Jiahui 

机构地区：[1]School of Statistics,Capital University of Economics and Business,Beijing 100070,China

出　　处：《Journal of Systems Science & Complexity》2024年第5期2104-2131,共28页系统科学与复杂性学报（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant No.12201431;the Young Teacher Foundation of Capital University of Economics and Business under Grant Nos.XRZ2022-070 and 00592254413070。

摘　　要：The dissemination of news is a vital topic in management science,social science and data science.With the development of technology,the sample sizes and dimensions of digital news data increase remarkably.To alleviate the computational burden in big data,this paper proposes a method to deal with massive and moderate-dimensional data for linear regression models via combing model averaging and subsampling methodologies.The author first samples a subsample from the full data according to some special probabilities and split covariates into several groups to construct candidate models.Then,the author solves each candidate model and calculates the model-averaging weights to combine these estimators based on this subsample.Additionally,the asymptotic optimality in subsampling form is proved and the way to calculate optimal subsampling probabilities is provided.The author also illustrates the proposed method via simulations,which shows it takes less running time than that of the full data and generates more accurate estimations than uniform subsampling.Finally,the author applies the proposed method to analyze and predict the sharing number of news,and finds the topic,vocabulary and dissemination time are the determinants.

关 键 词：Asymptotic optimality dissemination of news linear regression models model averaging optimal subsampling. 

分 类 号：O212.2[理学—概率论与数理统计] G206[理学—数学]