您的位置是:首页 > 学科动态

“社会经济大数据技术与应用”创新引智基地2017年外国专家授课安排

2017-06-06

统计与大数据研究院"社会经济大数据技术与应用"创新引智基地

2017年外国专家授课安排

 

授课教授:Professor Yanqing Sun

Department of Mathematics and Statistics

University of North Carolina at Charlotte, Charlotte,

North Carolina, USA.

 

课程名称:Survival and Event History Analysis


上课时间

 

下午14:00—17:30

上课地点

65

周一

第一讲Failure time data and censoringParametric models and likelihood functions

人民大学科研楼A702会议室

66

周二

第二讲One-sample nonparametric estimation

Counting processes and martingales

人民大学科研楼A702会议室

67

周三

第三讲The weighted log-rank tests for k-samples

人民大学科研楼A702会议室

68

周四

第四讲The Cox proportional hazards model

人民大学科研楼A702会议室

69

周五

第五讲Aalen`s additive hazards model

人民大学科研楼A702会议室

 


授课教授:Professor Huiyan Sang

Department of Statistics

Texas A&M UniversityCollege Station, TX

 

 

课程名称:Bayesian Modeling and Inference

上课时间

 

上午8:30-12:00

上课地点

66

周二

第一讲Bayesian Variable Selection ("big p" problem or high dimensional problem)

人民大学科研楼A702会议室

68

周四

第二讲Distributed Bayesian Inference ("big n" problem)

人民大学公共教学四4202

612

周一

第三讲Bayesian Models for Structured Big Data (time series, spatial data, and network data)

人民大学科研楼A702会议室

613

周二

第四讲Alternatives to Full Likelihood Function Based Bayesian MCMC (INLA, ABC and Bayesian Composite Likelihood)

人民大学科研楼A702会议室

 

  

授课教授:Professor Suojin Wang

Department of Statistics

Texas A&M UniversityCollege Station, TX

 

 

 

课程名称:Statistical Models and Inference II

上课时间

下午14:00—17:30

 

 

上课地点

67

周三

第一讲Semiparametric regression

 

人民大学科研楼A702会议室

614

周三

第二讲 Measurement error

人民大学科研楼A702会议室





  

授课教授:Professor Yanyuan Ma

           Department of Statistics

           University of South Carolina at Columbia,

           South Carolina, USA

 

课程名称:A Short Course on Semiparametrics and Applications

上课时间

 

下午14:00—17:30

上课地点

614日周三

A Short Course on Semiparametrics and Applications

第一讲

人民大学科研楼A702会议室

615日周四

A Short Course on Semiparametrics and Applications

第二讲

人民大学科研楼A702会议室

616日周五

A Short Course on Semiparametrics and Applications

第三讲

人民大学科研楼A702会议室

619日周一

A Short Course on Semiparametrics and Applications

第四讲

人民大学科研楼A702会议室





 

授课教授:Professor Edward J. Vytlacil

 Department of Economics

 Yale University, USA

 

 

 

 

课程名称:Selection Models, Treatment Effects, and the Econometric Evaluation of Policy Design

上课时间

 

上午8:30—12:00

上课地点

619日周一

第一讲 Motivation

人民大学明德商学院楼0105

620日周二

第二讲 Heterogeneity in program impacts, modeling self-selection, and parameter interest.

人民大学明德商学院楼0105

621日周三

第三讲Alternative Approaches

人民大学明德商学院楼0105

622日周四

第四讲Selection Models, Instrumental Variables, and the Marginal Treatment Effect

人民大学明德商学院楼0105

623日周五

第五讲Final

人民大学明德商学院楼0105

 

下午15:0016:00

 

623日周五

讲座:Marginal Treatment Effects in Theory and Practice

人民大学科研楼A702会议室

 


授课教授:Professor Xiaolin Li

  Department of Electrical and ComputerEngineering

  University of Florida , Gainesville

 

 

课程名称:Deep Learning

上课时间

上午8:30—12:00

下午14:00—17:30

上课地点

626日周一

第一讲 Deep Learning下午14:0017:30

 

人民大学科研楼A702会议室

627日周二

第二讲 Deep Learning下午14:0017:30

 

人民大学科研楼A702会议室

628日周三

第三讲Deep Learning上午8:3012:00

 

人民大学科研楼A702会议室

629日周四

第四讲Deep Learning上午8:3012:00

 

 

人民大学科研楼A702会议室

630日周五

第五讲Deep Learning上午8:3012:00

 

人民大学科研楼A702会议室





 

授课教授:Professor Runze Li

Department of Statistics

Penn State University

 

 

课程名称:Statistical Inference for High-dimensional Data

上课时间

上午9:00—11:00

 

上课地点

626日周一

第一讲 Statistical Inference for High-dimensional Data

 

人民大学科研楼A702会议室

627日周二

第二讲 Statistical Inference for High-dimensional Data

 

人民大学科研楼A702会议室





 

 

 

具体授课内容详见附件:

1. Professor Yanqing Sun

14:00—17:30 each dayJune 5 —June 9, 2017

Department of Mathematics and Statistics

University of North Carolina at Charlotte, Charlotte, North Carolina, USA.

Survival and Event History Analysis

Institute of Statistics and Big Data, Renmin University of China

The course introduces statistical models and methods in the analysis of survival data. Various methods are demonstrated through examples. The data analysis are pre-sented using statistical software R, which can be downloaded from www.r-project.org.

Many statistics packages can be downloaded from

http://cran.r-project.org/web/packages/

Tentative Topics:

l  Failure time data and censoring

l  Parametric models and likelihood functions

l  One-sample nonparametric estimation

l  Counting processes and martingales

l  The weighted log-rank tests for k-samples

l  The Cox proportional hazards model

l  Aalen`s additive hazards model

Reference Books

n  Thomas R. Fleming and David P. Harrington (1991). Counting Processes & Survival Analysis. John Wiley & Sons, Inc.

n  John Klein and Melvin Moeschberger (1997). Survival Analysis: Techniques for censored and truncated data. Springer-Verlag.

n  Jack D. Kalb eisch and Ross L. Prentice. (2002). The Statistical Analysis of Failure Time Data. Wiley, New York.

n  Torben Martinussen and Thomas Scheike (2006). Dynamic Regression Models for Survival Data. Springer, New York.

n  Odd O. Aalen, ­rnulf Borgan and Hakon K. Gjessing (2008). Survival and Event History Analysis. Springer, New York.

 

 

2. Yanyuan Ma

14:00—17:30each dayJune 14—June 19, 2017

Department of Statistics

University of South Carolina at Columbia, South Carolina, USA

A Short Course on Semiparametrics and Applications

Institute of Statistics and Big Data, Renmin University of China

 

Reference Books

n  Bickel, P. J., Klaassen, C. A. J., Ritov, Y. and Wellner, J. A. (1993) Efficient and Adaptive Estimation for Semiparametric Models

n  Van der Laan, M. J. and Robins, J. M. (2003) Unified Methods for Censored Longitudinal Data and Causality

n  Tsiatis, A. A. (2006) Semiparametric Theory and Missing Data

n  Kosorok, M. (2007) Introduction to Empirical Processes and Semiparametric Inference

3. Edward Vytlacilvy

8:30—12:00 each dayJune 19 —June 23, 2017

Department of Economics

New York University at 19 W. 4th Street, New York, USA

Selection Models, Treatment Effects, and the Econometric Evaluation of Policy Design

Institute of Statistics and Big Data, Renmin University of China

Structure:

The course consists of five days of approximately four hours of lectures per day.

 

Content:

The course is an applied micro-econometrics course on treatment effects and program evaluation,covering micro-econometric methods and illustrating those methods though applications in health,labor, and development economics. Our starting point will be to consider treatment effectparameters when (1) the effect of the treatment varies across individuals; and (2) selection intotreatment is possibly related to the idiosyncratic treatment effect. We then move beyond theconventional treatment effect parameters to consider the evaluation of alternativepolicies thatwould change the selection of individuals into treatment. We will consider alternative criteria forevaluating policies. Our focus will be on the evaluation of such programs using instrumentalvariables and selection models in the Marginal Treatment Effects framework, though we will alsoconsider other approaches including matching, regression discontinuity, and RCTs. Variousempirical applications will be used to illustrate the methodology. This course is a PhD level course.

 

Course Outline

1) Motivation. We introduce several empirical applications to provide motivation, includingexamples from health, labor, and development economics.

Readings:

n   Berry, James, Greg Fischer, and Raymond P. Guiteras. "Eliciting and utilizingwillingness to pay: Evidence from field trials in Northern Ghana." (2015), workingpaper,http://personal.lse.ac.uk/fischerg/Assets/BFG-EUWTP.pdf

n  Kowalski, Amanda E. Doing More When You`re Running LATE: ApplyingMarginal Treatment Effect Methods to Experiments. Working Paper, 2016.

http://www.iies.su.se/polopoly_fs/1.280153.1461580907!/menu/standard/file/mte_2016_03_24submit.pdf

n  Angrist, J. D., and W. N. Evans. "Children and their parents labor supply: evidencefrom exogenous variation in family size."AMERICAN ECONOMIC REVIEW 88.3(1998): 450-77. http://search.proquest.com/docview/233040193?pqorigsite=gscholar

n   Heckman, James J., and Xuesong Li. "Selection bias, comparative advantage andheterogeneous returns to education: evidence from China in 2000."Pacific EconomicReview 9.3 (2004): 155-171. http://onlinelibrary.wiley.com/doi/10.1111/j.1468-0106.2004.00242.x/full

 

2) Heterogeneity in program impacts, modeling self-selection, and parameter interest. Webriefly review structural models andcounter-factual notation. We then discuss possible waysto summarize the effect of an intervention when the effect varies across people, includingboth mean and distributional treatment parameters. We then consider alternative policychanges, and what information is required to evaluate proposed policy changes according toalternative criteria.

Readings:

n  James J Heckman and Jeffrey Smith. Evaluating the welfare state. In Econometrics andEconomic Theory in the 20th Century: The Ragnar Frisch Centennial Symposium,edited by S. Strom, number 31, Cambridge University Press, 1998.http://www.nber.org/papers/w6542

 

3) Alternative Approaches. We cover alternative approaches to evaluate treatment effects,including randomized controlled trials, panel data (fixed effects, difference-in-difference)methods, matching methods, instrumental variables, selection models, and regressiondiscontinuity methods. We also cover bounding/set-identification approaches. We illustratethe methods through a series of empirical applications.

Readings:

n  Heckman, James J., and Jeffrey A. Smith. "Assessing the case for socialexperiments."The Journal of Economic Perspectives 9.2 (1995): 85-110.http://www.jstor.org/stable/2138168?seq=1 - page_scan_tab_contents

n  Smith, Jeffrey A., and Petra E. Todd. "Does matching overcome LaLonde`s critique ofnonexperimental estimators?."Journal of econometrics 125.1 (2005): 305-353.

http://www.sciencedirect.com/science/article/pii/S030440760400082X

n  Heckman, James. "Instrumental variables: A study of implicit behavioral assumptionsused in making program evaluations."Journal of human resources (1997): 441-462.

http://www.jstor.org/stable/146178

n  Guido W Imbens and Joshua D Angrist. Identification and estimation of local averagetreatment effects. Econometrica, 62(2):467–475, 1994.

https://scholar.harvard.edu/files/imbens/files/identification_and_estimation_of_local_average_treatment_effects.pdf

n   Lee, David S., and Thomas Lemieux. "Regression discontinuity designs in socialsciences."Regression Analysis and Causal Inference, H. Best and C. Wolf (eds.),Sage (2014). http://econ.sites.olt.ubc.ca/files/2014/02/Lee-Lemieux-rev.pdf

 

4) Selection Models, Instrumental Variables, and the Marginal Treatment Effect. Weconsider the structure of parametric, semi-parametric, and non-parametric selection models,and relate them to the independence and monotonicity assumptions imposed in the LATEframework. We analyze the identification and estimation of treatment effects whilecontrolling for self-selection. We focus on the Marginal Treatment Effect parameter (MTE),and consider how the shape of the MTE function can provide guidance on whether aprogram currently in place is targeting those individuals who would most benefit from theprogram. We illustrate the methods through a series of empirical applications.

Readings:

n  James J Heckman, Sergio Urzua, and Edward Vytlacil. Understanding instrumentalvariables in models with essential heterogeneity. The Review of Economics andStatistics, 88(3):389–432,2006.

http://www.mitpressjournals.org/doi/pdf/10.1162/rest.88.3.389

n  Aakvik, Arild, James Heckman, and Edward Vytlacil (2005), "Treatment Effects ForDiscrete Outcomes when Responses To Treatment Vary Among ObservationallyIdentical Persons: An Application to Norwegian Vocational Rehabilitation Programs,"Journal of Econometrics, March-April 2005, 125(1-2): 15-51.

http://jenni.uchicago.edu/papers/pku_2007/Aakvik_Heckman_etal_2005_JoE_v125_n1-2.pdf

n   Carneiro, Pedro, James J. Heckman, and Edward J. Vytlacil. "Estimating marginalreturns to education."The American economic review 101.6 (2011): 2754-2781.

https://www.aeaweb.org/articles?id=10.1257/aer.101.6.2754

n  Brinch, Christian N., Magne Mogstad, and Matthew Wiswall. "Beyond LATE with adiscrete instrument. Heterogeneity in the quantity-quality interaction of children."Forthcoming in Journal of Political Economy.

https://sites.google.com/site/magnemogstad/manu1111_final_December_2015_JPE.pdf?attredirects=0&d=1

n   Doyle Jr, Joseph J. "Child protection and adult crime: Using investigator assignment toestimate causal effects of foster care."Journal of political Economy 116.4 (2008): 746-770. http://www.journals.uchicago.edu/doi/abs/10.1086/590216

n  Maestas, Nicole, Kathleen J. Mullen, and Alexander Strand. "Does disability insurancereceipt discourage work? Using examiner assignment to estimate causal effects of SSDIreceipt." (2013). American Economic Review, 103(5): 179701829.

https://eml.berkeley.edu/~saez/course/maestas-mullen-strandAER13.pdf

 

Lecture_Renmin_Intro

lectures_Renmin_I

lectures_Renmin_II

lectures_Renmin_III


 

4.授课教授:Professor Xiaolin Li 

         Department of Electrical and Computer Engineering

         University of Florida , Gainesville

8:3012:00 each dayJune 26June 302017

 

课程名称:Deep Learning

Abstract:Deep Learning The tremendous big data generated from natural systems, engineered systems, and human activities require new capabilities in algorithms and systems to explore insights and make decisions. To address the challenges of big data, this course covers the full spectrum of big data ecosystems: algorithms, systems, and big data analytics at scale. It consists of an overview of representative data mining, statistics, and machine learning algorithms.  We will explore major paradigms in deep learning, from supervised learning, unsupervised learning, to reinforcement learning. Real-world case studies will be explored in science, engineering, business, and health.

 

5.授课教授:Professor Runze Li 

            Department of Statistics

            Penn State University

9:0011:00 each day, June 26June 27, 2017

 

课程名称:Statistical Inference for High-dimensional Data

Abstract: Tests of high dimensional means and covariance structures have received a lot of attentions in the recent literature. This short course introduces statistical procedures for test of high dimensional mean and high dimensional covariance structures.