• 统计研究中心
当前位置: 首页 > 系列讲座 > 正文

Georgetown University Ming T. Tan教授: Robust Estimates of Rx Effect via Semi-Parametric Models in MRCT and Statistical Generalizations

光华讲坛——社会名流与企业家论坛第5495期

主题:Robust Estimates of Rx Effect via Semi-Parametric Models in MRCT and Statistical Generalizations

主讲人:Georgetown University Ming T. Tan教授

主持人:统计学院统计研究中心 林华珍教授

时间:2019年7月19日下午4:00-5:00

地点:西南财经大学柳林校区弘远楼408会议室

主办单位:统计研究中心 统计学院 科研处

主讲人简介:

Dr. Tan has been professor and chair of the Department of Biostatistics, Bioinformatics and Biomathematics at Georgetown University since 2012 (http://dbbb.georgetown.edu). He came to Georgetown in 2012 from University of Maryland School of Medicine and the University of Maryland Marlene and Stewart Greenebaum Cancer Center, where had been Professor and director of biostatistics since 2002. He was previously a senior member (faculty) at St. Jude Children's Research Hospital Cancer Center and biostatistics director of St Jude's Developmental Therapeutics for Solid Malignancies Program (1997-2002), assistant and associate staff/professor of Biostatistics and Epidemiology at The Cleveland Clinic (1990-1997). He received his Ph.D. in Statistics in 1990 from Purdue University, West Lafayette, Indiana.

Dr. Tan’s research covers the design, monitoring and analysis of clinical trials (in both multi-center and single institutional settings), laboratory investigations, biomarker evaluation, genomics and epidemiological research. His current research focuses on developing statistical methods for multidrug combinations utilizing experimental data, pharmacology, systems biology, methods for the adaptive design and efficiently analysis of clinical trials and subgroups incorporating multiple genomic markers; and bioinformatics approaches for high dimensional genomics data in Cancer Epidemiology, with funding support from NCI and NHLBI.

Dr. Tan has served on multiple NIH study sections (such as Clinical Oncology and Epidemiology of Cancer), review and site visit panels (such as the P30, P50, and P01), Data and Safety Monitoring Boards for government, institution and pharmaceutical trials, and has been a member of FDA Advisory Committee (recent term to 2018). He is a Fellow of the American Statistical Association since 2007 and an elected Member of the International Statistical Institute. He is current an Executive Editor of Molecular Carcinogenesis, Associate Editor of Statistics in Medicine and Drug Design, Development and Therapy, and a senior editor of Journal of Clinical and Translational Science, and statistical consultant to Nature including Nature Medicine and Nature Biotechnology. He has more than 200 peer reviewed publications split about evenly between statistics/biostatistics methodology and biomedicine journals.

谭博士自2012年以来一直担任乔治城大学生物统计学、生物信息学和生物数学学系的教授和系主任(http://dbbb.georgetown.edu)。他于2012年来到乔治城大学,此前自2002年起他一直在马里兰大学医学院、马里兰大学Marlene and Stewart Greenebaum癌症中心担任生物统计学教授和主任。他还曾担任过St. Jude儿童研究医院癌症中心高级成员(教职工)、St Jude固体恶性肿瘤发展治疗项目生物统计学主任(1997-2002)、Cleveland诊所生物统计学和流行病学助理和副教授(1990-1997)。他于1990年在印第安纳州普渡大学获得统计学博士学位。

谭博士的研究涵盖临床试验设计、监测和分析(包括多中心环境和单一机构)、实验室调查、生物标志物评估、基因组学和流行病学研究。他目前的研究重点是开发多药物组合的统计方法,综合运用实验数据、药理学、系统生物学和用于临床试验和包含多基因组标记的子组的适应性设计和有效分析的方法;此外还包括在NCI和NHLBI的资助下,为癌症流行病学中的高维基因组数据提供生物信息学方法。

谭博士曾在多个NIH研究部门(如临床肿瘤学和癌症流行病学),审查和现场访问小组(如P30,P50和P01),政府,机构和药物试验的数据和安全监测委员会任职,并一直是FDA咨询委员会的成员(近期至2018年)。 他自2007年起担任美国统计协会会员,并且是国际统计学会成员。现为《分子癌变》执行主编、《医学与药物设计、开发与治疗统计》副主编、《临床与转化科学杂志》高级编辑、《自然医学》、《自然生物技术》等《自然》杂志统计顾问。他拥有200多篇同行评审的论文,这些论文在统计学/生物统计学方法论和生物医学期刊中分布相当。

主要内容:

Multiregional randomized clinical trials (MRCT) are increasingly common in drug development. With China joining ICH in 2016 and the publication of E17, it is of current and long term interest to resolve statistical issues in MRCT. In this talk I will highlight some key statistical issues, e.g., increased heterogeneity in trials involving different regions in the world. So accurate estimate of variance would be important to obtain more accurate sample size estimate. Most current methods for the assessment of the consistency or similarity of the treatment effect between different ethnic groups based on some subjectively specified model. We propose a novel semi-parametric model and show that it can give robust estimates of the regional treatment effects. The model is estimated by maximizing profile likelihood using EM. The prole likelihood ratio statistic is used to test the existence of regional differences. We derived the asymptotic properties of the estimate and show that semiparametric model performs well by simulation. We then discuss applications to two clinical trials. Last but least we discuss the importance of the statistical generalizations of the development in categorical regression models (This work is in collaboration with Ao Yuan, Yizhao Zhou, Chongyang Duan and Shuxin Wang).

多区域随机临床试验(MRCT)在药物开发中的使用越来越普遍。随着中国2016年加入ICH和E17的发布,解决MRCT中的统计问题已成为当前也将是长期的研究热点。本次交流中,我将强调一些统计上的关键问题,例如在涉及世界不同地区的试验中出现的异质性问题。因此,准确的方差估计对于获得更准确的样本量估计至关重要。目前,评价不同民族之间治疗效果的一致性或相似性的方法大多是基于一些主观指定的模型。据此,我们提出了一种新的半参数模型,并证明出该模型能够得到区域治疗效果的可靠估计。该模型通过使用EM算法最大化边侧似然来进行估计。边侧似然比统计量也可以用来检验区域差异的存在性。进一步,我们推导了该估计的渐近性质,并表明该半参数模型仿真效果良好,并将此方法应用于两个临床试验中。最后,我们讨论了在分类回归模型中发展统计概括的重要性。(这项工作是与Ao Yuan, Yizhao Zhou, Chongyang Duan, Shuxin Wang合作)


上一条:中国科学院数学与系统科学研究院 陈敏研究员: Semi-parametric inference for large-scale data with non-stationary non-Gaussian temporally dependent noises

下一条:新加坡国立大学赵安琪博士:To Adjust or not to Adjust? Estimating the Average Treatment Effect in Randomized Experiments with Missing Covariates