Title (题目): Statistics in the Pharmaceutical Industry
Time (时间): 1pm-2pm, 2015-11-26 (Thursday)
Location (地点): 伟清楼209 (Center for Statistical Science, Tsinghua University)
Speaker (报告人): Shu Yang, Novartis Pharmaceuticals Corporation

Abstract (摘要):
This talk gives an overview of the process of drug development and how statistics is used in pharmaceutical industry. The unique statistical problems and techniques are discussed for each phase of the drug development. Specifically, for pre-clinical study, the problem of assay design and analysis of small sample size data are discussed; for phase I/II dose finding trials, designs using 3+3 or Bayesian Logistic Regression Model are discussed; for phase I clinical pharmacology trials, the use of mixed effect is discussed; for phase II/III trials, group sequential design and survival analysis are discussed. In addition, other popular statistical methods in pharmaceutical industry such as matching and statistical classification (subgrouping) are also discussed.

About the speaker (报告人介绍)
Shu Yang currently works as a senior principal statistician in Oncology department of Novartis Pharmaceuticals. She obtained her BS degree in applied math from Statistics department of School of Mathematics Science, and then obtained her MS degree in Signal Processing from Center of information science of Peking University. She obtained her PhD degree in Mathematics (Statistics concentration) from department of Mathematics and Statistics in Boston University.

Her PhD research direction is to model the high dimensional network data with statistical models, such as simultaneous Lasso regression, and Bayesian optimal design. Her current research interest is in modeling the drug exposure response data with mixed effect models and Bayesian hierarchical models.

Title (题目): Latent Variable and Network Models for Measurement
Time (时间): 4pm-5pm, 2015-11-16 (Monday)
Location (地点): 伟清楼209 (Center for Statistical Science, Tsinghua University)

Speaker (报告人): Jingchen Liu, Columbia University

Abstract (摘要):
One of the main tasks of statistical models is to characterize the dependence structures of multi-dimensional distributions. Latent variable model takes advantage of the fact that the dependence of a high dimensional random vector is often induced by just a few latent (unobserved) factors. In this talk, we present several problems regarding latent variable models in the context of measurement theory. When the dimension grows higher and the dependence structure becomes more complicated, it is hardly possible to find a low dimensional parametric latent variable model that fits well. We further enrich the model by including a network structure on top of the latent structure. Thus, the main variation of the random vector remains governed by latent variables and the network captures the remainder dependence. Both have interpretations in practice.

About the speaker (报告人介绍)
Jingchen Liu received his Ph.D. in Statistics from Harvard University in 2008. He is now an associate professor in statistics at Columbia University. He is the winner of 2013 Tweedie New Researcher Award and co-winner of 2009 Best Publication in Applied Probability Award.

Title (题目): Regression analysis of additive hazards model with latent variables
Time (时间): 2015/11/2(星期一), 16:00-17:00
Location (地点): 伟清楼209（统计学研究中心会议室）
Speaker (报告人): 孙六全，中国科学院数学与系统科学研究院

Abstract (摘要):
We propose an additive hazards model with latent variables to investigate the observed and latent risk factors of the failure time of interest. Each latent risk factor is characterized by correlated observed variables through a confirmatory factor analysis model. We develop a hybrid procedure that combines the EM algorithm and the borrow-strength estimation approach to estimate the model parameters. The consistency and asymptotic normality of the parameter estimators are established. Various nice features including finite sample performance of the proposed methodology are demonstrated by simulation studies. Our model is applied to a study concerning the risk factors of chronic kidney disease for type 2 diabetic patients.

About the speaker (报告人介绍):

孙六全研究员1998年于北京大学获博士学位。同年，进入中国科学院数学与系统科学研究院应用数学所从事博士后研究，并历任助理研究员、副研究员和研究员等职务。孙六全研究员在生存分析、生物与医学统计、复发事件和纵向数据的统计推断、不完全观察数据的统计分析等领域做出了一系列重要学术成果，在国际顶级统计学期刊发表了大量高水平学术论文。2008年，获中国科学院数学与系统科学研究院突出科研成果奖。他还是中国概率统计学会的副理事长。