報(bào) 告 人：孫六全 教授

報(bào)告題目：Mark-Specific Quantile Regression Model

報(bào)告時(shí)間：2023年10月21日（周六上午11：00 )

報(bào)告地點(diǎn)：徐州溫德姆酒店博頓A廳

主辦單位：數(shù)學(xué)研究院、數(shù)學(xué)與統(tǒng)計(jì)學(xué)院、科學(xué)技術(shù)研究院

報(bào)告人簡(jiǎn)介：

       孫六全，中國(guó)科學(xué)院數(shù)學(xué)與系統(tǒng)科學(xué)研究院二級(jí)研究員，博士生導(dǎo)師，中國(guó)科學(xué)院數(shù)學(xué)與系統(tǒng)科學(xué)研究院統(tǒng)計(jì)中心副主任。現(xiàn)任中國(guó)現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)副理事長(zhǎng)，北京應(yīng)用統(tǒng)計(jì)學(xué)會(huì)副會(huì)長(zhǎng)，中國(guó)統(tǒng)計(jì)教育學(xué)會(huì)高等教育分會(huì)副會(huì)長(zhǎng)，中國(guó)現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)資源與環(huán)境統(tǒng)計(jì)分會(huì)理事長(zhǎng)，全國(guó)工業(yè)統(tǒng)計(jì)學(xué)教學(xué)研究會(huì)監(jiān)事會(huì)會(huì)長(zhǎng)，全國(guó)工業(yè)統(tǒng)計(jì)教學(xué)研究會(huì)數(shù)字經(jīng)濟(jì)與區(qū)塊鏈技術(shù)協(xié)會(huì)會(huì)長(zhǎng)?，F(xiàn)為《數(shù)理統(tǒng)計(jì)與管理》主編，以及《統(tǒng)計(jì)與決策》、Journal of Systems Science and Complexity、Statistics and Its Interface、Journal of Biometrics & Biostatistics等期刊的編委，科學(xué)出版社《數(shù)學(xué)大辭典》數(shù)理統(tǒng)計(jì)篇編委，中國(guó)第二屆數(shù)學(xué)名詞審定委員會(huì)委員，《中國(guó)大百科全書(shū)》第三版統(tǒng)計(jì)學(xué)科副主編，《中國(guó)大百科全書(shū)》第三版數(shù)學(xué)學(xué)科編委兼數(shù)理統(tǒng)計(jì)學(xué)分支主編。曾任中國(guó)概率統(tǒng)計(jì)學(xué)會(huì)副理事長(zhǎng)，《中國(guó)科學(xué)，數(shù)學(xué)》等期刊編委，國(guó)際華人統(tǒng)計(jì)協(xié)會(huì)（ICSA）Program Committee Member（2018-2020），國(guó)際華人統(tǒng)計(jì)協(xié)會(huì)（ICSA） Membership Committee Co-Chair（2020-2021）。主要研究方向?yàn)樯娣治?、生物統(tǒng)計(jì)、縱向數(shù)據(jù)和復(fù)發(fā)事件數(shù)據(jù)以及復(fù)雜刪失數(shù)據(jù)的統(tǒng)計(jì)分析。在JASA，Biometrik，JMLR及SMMR等國(guó)內(nèi)外核心期刊發(fā)表學(xué)術(shù)論文170余篇。主持了國(guó)家自然科學(xué)基金重點(diǎn)項(xiàng)目一項(xiàng)，并先后主持或參與了973重大項(xiàng)目、國(guó)家自然科學(xué)基金重大項(xiàng)目、重點(diǎn)項(xiàng)目和面上項(xiàng)目等20項(xiàng)。 

報(bào)告摘要：

       Quantile regression has become a widely used tool for analyzing survival data. However, quantile regression for survival data with continuous marks is still scarce. In this article, we propose a novel mark-specific quantile regression model to address this problem. Our method borrows strength from data in a neighborhood of a mark to estimate the regression coefficients, which is very different from the existing methods for competing risks data with discrete causes. The asymptotic properties of the resulting estimators are established across mark and quantile continuums. In addition, a mark-specific quantile-type vaccine efficacy is proposed and its statistical inference procedures are developed. Simulation studies are conducted to evaluate the finite sample performances of the proposed estimation and hypothesis testing procedures. An application to the first HIV vaccine efficacy trial is provided.