学术交流
学术交流
首页  >  学术科研  >  学术交流  >  正文

    Mathematics Outlook Forum---Statistics Series Report

    2020-11-27 金沙威尼斯欢乐娱人城 点击:[]

    Speaker: Li Yaguang, Postdoctoral Fellow, University of Toronto

    Reporting time: 9:00-9:30 am on December 5th

    Report location: Tencent Conference ID 504 790 537

    Title:A modelbased multithreshold method for subgroup identification

    Summary:Thresholding variable plays a crucial role in subgroup identification for personalized medicine. Most existing partitioning methods split the sample based on one predictor variable. In this paper, we consider setting the splitting rule from a combination of multivariate predictors, such as the latent factors, principle components, and weighted sum of predictors. Such a subgrouping method may lead to more meaningful partitioning of the population than using a single variable. In addition, our method is based on a change point regression model and thus yields straight forward modelbased prediction results. After choosing a particular thresholding variable form, we apply a twostage multiple change point detection method to determine the subgroups and estimate the regression parameters. We show that our approach can produce two or more subgroups from the multiple change points and identify the true grouping with high probability. In addition, our estimation results enjoy oracle properties. We design a simulation study to compare performances of our proposed and existing methods and apply them to analyze data sets from a Scleroderma trial and a breast cancer study.


    Speaker: Zhang Jia, Postdoctoral fellow, Southwestern University of Finance and Economics

    Reporting time: 9:30-10:00 am on December 5th

    Report location: Tencent Conference ID 504 790 537

    Title:High Dimensional Elliptical Sliced Inverse Regression in non-Gaussian Distributions

    Summary:Sliced inverse regression (SIR) is the most widely-used sufficient dimension reduction method due to its simplicity, generality and computational efficiency. However, when the distribution of the covariates deviates from the multivariate normal distribution, the estimation efficiency of SIR gets rather low, and the SIR estimator may be inconsistent and misleading, especially in high-dimensional setting. In this paper, we propose a robust alternative to SIR - called elliptical sliced inverse regression (ESIR) for analyzing high-dimensional, elliptically distributed data. There are wide applications of the elliptically distributed data, especially in finance and economics where the distribution of the data is often heavy-tailed. To tackle the heavy-tailed elliptically distributed covariates, we novelly utilize the multivariate Kendall's tau matrix in a framework of generalized eigenvalue problem in sufficient dimension reduction. Methodologically, we present a practical algorithm for our method. Theoretically, we investigate the asymptotic behavior of the ESIR estimator under high-dimensional setting. Simulation results show that ESIR significantly improves the estimation efficiency in heavy-tailed scenarios. Analysis of the Istanbul stock exchange data set also demonstrates the effectiveness of our proposed method. Moreover, ESIR can be easily extended to other sufficient dimension reduction methods and applied to non-elliptical heavy-tailed distributions.



    Speaker: Wang Yang Shanghai Jiao Tong University Postdoc

    Reporting time: 10:00-10:30 am, December 5th

    Report location: Tencent Conference ID 504 790 537

    Title:A Kernel Regression Model for Panel Count Data with Nonparametric Covariate Functions

    Summary:Local kernel pseudo-partial likelihood is used for estimation in panel count model with nonparametric covariate functions. Estimator of the derivative of nonparametric covariate function is derived first and nonparametric function estimator is then obtained by integrating the derivative function. Under some regularity conditions, uniform consistency rates and pointwise asymptotic normality are obtained for the local derivative estimator. Moreover, the baseline function estimator is shown to be uniformly consistent. The demonstration of the asymptotic results relies strongly on the modern empirical theory, which not require the Poisson assumption. Simulation studies also show that the local derivative estimator performs well in finite-sample regardless of whether or not the Poisson assumption holds. We also apply the proposed methodology to analyze a clinical study on childhood wheezing.




    Speaker: Zhang Shuxiong, PhD, Beijing Normal University

    Reporting time: 10:30-11:00 am on December 5th

    Report location: Tencent Conference ID 504 790 537

    Title:On large deviation probabilities for empirical distribution of the branching random walk with heavy tails

    Summary:


    上一条:数学展望论坛---数学系列报告
    下一条:数学展望论坛---统计系列报告

    关闭

Baidu
sogou