講座編號:jz-yjsb-2022-y006
講座題目:Spatial-temporal Model with Heterogeneous Random Effects
主 講 人:馮興東 教授 上海財經大學
講座時間:2022年4月13日(星期三)下午14:00
講座地點:騰訊會議,會議ID:851 813 567
參加對象:數學與統計學院全體教師及研究生
主辦單位:數學與統計學院、研究生院
主講人簡介:
馮興東,上海財經大學統計與管理學院院長、統計學教授、博士生導師。研究領域為數據降維、穩健方法、分位數回歸以及在經濟問題中的應用、大數據統計計算、強化學習等,在國際頂級統計學期刊Journal of the American Statistical Association、Annals of Statistics、Journal of the Royal Statistical Society-Series B、Biometrika以及人工智能頂會NeurIPS上發表論文多篇。2018年入選國際統計學會推選會員(Elected member),2019年擔任全國青年統計學家協會副會長以及全國統計教材編審委員會第七屆委員會專業委員(數據科學與大數據技術應用組),2020年擔任第八屆國務院學科評議組(統計學)成員,2022年擔任全國應用統計專業碩士教指委委員,兼任國際統計學權威期刊Annals of Applied Statistics編委(Associate Editor)以及國內統計學權威期刊《統計研究》編委。
主講內容:
In this paper, we propose a novel spatial-temporal model with individual random effects characterized by a location-scale structure, which allows us to flexibly capture the pure influence of space-specific factors in the framework of quantile regression.
A hybrid two-stage estimation procedure is introduced for this model, where the first stage proposes a Gaussian quasi-maximum likelihood estimator (QMLE) for the spatial-temporal effects while the second stage constructs a weighted conditional quantile estimator (WCQE) to study the conditional quantiles of the random effects related to space-specific attributes.
The validity of the two-stage hybrid estimation is verified, and the asymptotic properties of our estimators are established.
Our simulation study indicates that the proposed estimation procedure performs well in different scenarios with finite samples, and a real case study on the air quality of China is used to illustrate the application of the proposed method.
