The University of ConnecticutDepartment of Statistics

Graduate Program

Founded in 1963, the Department is one of the major statistics departments in the Northeast and hasnational and international recognition in both teaching and research. Core faculty have research interests in majorareas of probability and statistics, spanning virtually all modern areas of statistical applications. Graduate education has been a traditional strength of the Department with over 60 Ph.D. and 140 M.S.degrees awarded in the last 10 years. The graduate program balances theory, methods and applications, including asolid foundation in mathematical statistics, probability theory, statistical methodology and modeling, data analysis,and computational statistics. Elective courses are regularly given in active areas of research with emphasis onmodern and model based statistical methodology.

Graduates of the program promptly move into attractive positions in academics, government, and industry,specific areas including biology, medicine, business, economics, engineering, and the social sciences.

Programs of Study

The Department of Statistics offers programs leading to M.S. in Statistics, Professional M.S. in Biostatisticsand Ph.D. degrees. All programs include training in statistical application and theory, and give students sufficientflexibility to pursue their special interests as well as time to take courses in other departments at UCONN.

The M.S. program in statistics requires 8-10 courses, depending on a student’s previous academic record.While it is possible to complete the M.S. degree within a year, most students will need three or four semesters. Thecore courses of the program cover mathematical statistics, linear models, design of experiments, and appliedstatistics; please see the description of the M.S. program for more detail. Students are encouraged to participate instatistical consulting projects done by members of the Department.

The professional M.S. program in Biostatistics requires 10 courses, which will focus on practical skills thatare sought after in health related fields, including pharmaceutical sciences and genomics. Students completing thisprogram successfully will acquire expertise in topics including statistical inference, linear regression, analysis ofvariance, design and analysis of clinical trials and epidemiological studies, programming in SAS and R, andconsulting. Please see the description of the M.S. Biostatistics program for more detail.

Both MS programs will give you a solid foundation in theory and methods of statistics, so you also will beable to find a job in industry, or to continue your study as a PhD candidate.

The Ph.D. program emphasizes development of the ability to generate novel results in statistical methods,statistical theory, or probability. The course work typically consists of at least sixteen graduate level courses thatcover a wide range of topics, including mathematical statistics, linear models, statistical inference, applied statistics,real analysis, and probability. After completing the necessary course work and a sequence of examinations, a Ph.D.candidate must complete a dissertation that makes an original contribution to the field of statistics or probability.The dissertation may be predominantly development of novel statistical methodology for an area of application. Formore detail, please see the description of the Ph.D. program for more detail.

1

Research Facilities

Research and teaching Labs for the Department of Statistics are housed in the Philip E. Austin Building. TheDepartment has a teaching computer lab and a research computer lab. The Department has as 21 seat research labwith a mix of Intel-based Linux and Windows systems dedicated to large scale numerical computing and statisticalsimulation. The Department also has a Linux based computer cluster with over 300 CPU’s for computing intensivestatistical research. A large software base is now available in either the PCs or the Linux workstations in both labs,which includes SAS, S-Plus, SPSS, GLIM, MINITAB, Mathematica, Maple, IMSL (Fortran and C), R, OpenBUGS, as wellas other packages and languages. IMSL (Fortran and C) and R are also available in the department Linux cluster.Both the research lab and computing cluster are accessible to PhD students, visiting scholars, and faculty members.

The teaching lab exclusively features Windows machines with similar software bundles and is used for bothgraduate and undergraduate computing classes. When not in use for teaching, the lab is open to all students withteaching assistants on duty to serve as tutors.

The Department’s computers are managed and maintained by four lab managers, a Linux quarter timeoperations manager and a PC quarter time operations manager from the office of the Dean of the College of LiberalArts and Sciences, and a student Linux cluster manager and a student Webmaster. The computer managementteam maintains, installs, and upgrades the operating systems and software, and they also provide the service ofweekly tape-backing up as well as daily trouble-shooting of system problems.

2

Financial Aid

Graduate teaching and research assistantship and fellowship-assistantship combinations are available (toqualified students in the Ph.D. program) covering tuition and health benefits with a stipend of $20,965-$24,526 fora 100% Graduate Assistant for the academic year 2015-2016. Some internships and financial aid are available in thesummer. Students with full aid generally take three courses a semester. Those with a fellowship-assistantship maytake four courses. Outstanding students may be awarded University predoctoral fellowships. Advanced students areconsidered for research assistantship.

Cost of Study/Living and Housing Costs

Please refer to the Graduate School website for information on tuition, www.grad.uconn.edu/tuition and Residential Life for information on housing, www.reslife.uconn.edu.

Student Group

There are close to 120 graduate students in the department, approximately 75 working towards an M.S.degree and 43 for the Ph.D. degree. The department has been granting 6-7 Ph.D. degrees a year. All graduatestudents and faculty have office space within the department, creating an open, informal environment. Of the 33Ph.D. recipients in the last five years, 11 have academic tenure track positions, 20 in industry and 1 in government.The M.S. recipients have positions with the government, industry and business, and academic research centers. Aspredicted by the National Science Foundation, employment opportunities for persons with degrees in statisticscontinue to be excellent.

Location

The University of Connecticut’s main campus is in northeastern Connecticut, 25 miles from Hartford, in anattractive rural area. It is about 1-1/2 hours by car from Boston and 3 hours from New York City.

The University

The University of Connecticut, which celebrated its centennial in 1981, is the state of Connecticut’s land-grant institution. It has about 30,000 students, including more than 8,000 in graduate study. Its substantial, but notoverwhelming, size allows the University to offer a broad curriculum and an excellent program of concerts, plays,and other cultural events.

The Department of Statistics was founded in 1963. Its faculty members conduct an active and prolificresearch program in which students are involved as soon as possible.

3

Application information

Applicants who wish to be considered for financial aid should apply for fall admission and must submit acomplete application to the University by February 1. Please note that financial aid is only available for Ph.D.applicants. Applicants not seeking financial aid can apply until June 1 for fall admission and until October 1 forspring admission, however, spring admission is typically reserved for current UConn students.

Most of our students come from undergraduate Mathematics or Statistics majors. Persons with degrees infields other than Statistics and Mathematics are encouraged to apply.

While there are no official course requirements for admission, a level of mathematical sophistication andstatistical knowledge is necessary for acceptable progress. At the minimum, this amounts to (1) three semesters ofcalculus, including one semester of multivariate calculus (2) one semester of linear algebra, and (3) two semestersof undergraduate statistics. Course work to remedy deficiencies can be taken while in the program.

The following are basic criteria for the evaluation of an application:

GRE scores: Taken within 5 years with a verbal score above the median and a quantitative scoreranked in the top twenty five percent for financial support. Please note that in August 2011, therewere substantial changes in the GRE general test. GRE scores from the old exam format (but no olderthan 5 years) will still be accepted. For more information, go to the official GRE website atwww.ets.org/gre.

English Proficiency: If you are not a native speaker of English, you must submit evidence of yourproficiency in the English language. You may use the (no more than 2 years old) results from eitherone of the two standardized tests to satisfy this requirement. If you submit results from the Test ofEnglish as a Foreign Language (http://www.ets.org/toefl/) (TOEFL), you need a minimum overall scoreof 550 for the paper-based test, or 79 for the internet-based test. If you submit results from theInternational English Language Testing System (http://www.ielts.org) (IELTS), you need an averageoverall band score of at least 6.5. Only the scores from the Academic Module, not the GeneralTraining Module, are applicable. If you submit results from the Person Test of English (PTE) werequire an overall score of 53. Applicants who have a degree from a college in the U.S. can have thescore waived, however, for Ph.D. applicants who want to be considered for a teaching assistantship,TOEFL scores are required.

Transcripts: You must submit all applicable, official transcripts (undergraduate & graduate). Yourtranscript(s) must meet the following criteria:

-A cumulative grade-point average of 3.0 for your entire undergraduate career or

-A grade-point average of at least 3.0 for your last two undergraduate years or

-Exceptional work in your entire final undergraduate career (3.5 or better) or

-Graduate work with a minimum grade-point average of 3.0 or better.

Cont’d next page

4

Letters of Recommendation: Three letters of recommendation should accompany each application. Students should request letters from teachers who know them well, preferably from their last two years of coursework.

Personal Statement: A letter describing your career goals.

Applications are submitted through the graduate school website, www.grad.uconn.edu

Department of Statistics Ph.D. Program

For students entering the program after a Bachelors Degree, typically 16 to 18 courses are required. Anindividual plan of study is developed by the student and his or her Advisory Committee.

Knowledge of a sequence of core courses is required for all Ph.D. students. These courses are 5585-5685(Mathematical Statistics), 5505-5605 (Applied Statistics), 5725, 6694 (Linear Models), 6315, 6515 (Theory ofStatistics), 6325-6894 (Measure Theory and Probability Theory), 5515 (Design of Experiments), giving a total of 33credits for core courses. Additional credits can be earned from the list of elective courses.

In general, Ph.D. students are required to elect 1 – 2 courses from other departments. However, it issufficient to take one graduate level course from the Department of Mathematics. Ph.D. students are alsoencouraged to take courses in Computer Science as well as in application areas such as Biology or Economics. Theelected course(s) must be approved by the major advisor of a student. Under certain circumstances, a majoradvisor can exempt his/her student from the above requirement, if the student has had internships or RA’s ininterdisciplinary areas. The Department has no requirement on foreign languages.

The first formal departmental requirement for the Ph.D. program is successfully passing the Ph.D. QualifyingExamination which is a written test of certain basic courses to the program. The next requirement is passing of theGeneral Examination which is given as an oral test and covers aspects of Applied Statistics, Linear Models,Probability Theory and Statistics. The preparation of a dissertation then follows which must present an originalcontribution to the general area of Statistics and/or Probability. The final requirement of the program is a defenseof the Ph.D. dissertation before an audience of interested members of the department.

The Department expects every Ph.D. student to strive to finish his or her study within 4 years. For studentsarriving without a M.S. degree in Mathematics or Statistics, the Department may provide up to 5 years of financialsupport. For those arriving with such a degree, the Department may provide up to 4 years of financial support.

Notes:

In order to receive continuous support, Ph.D. students with financial support should maintain suitable course load. Each should take at least 3 courses in each semester until taking the Ph.D. Qualifying Examination. For students arriving with a Bachelor’s Degree and receiving financial support from the Department, we propose the following timetable for these examinations:

1. Ph.D. Qualifying Examination: within 3 semesters from start of program.

5

2. General Examination: within 6 semesters from start of program.

3. Ph.D. Thesis Defense: no later than 5 years from start of program.

In order for a student currently enrolled in our M.S. program to switch to the Ph.D. program or to be considered for financial support, he or she must first pass both parts of the Ph.D. Qualifying Exam at Ph.D. level.

Master's Degree in Statistics

The M.S. program emphasizes applied statistics and requires students to take at least one course in areas ofapplication. The plan of study for this degree may be formulated with related work in almost any area, e.g., Biology,Business, Economics, Nutrition, and Psychology to name a few.

Individuals with a Bachelor’s degree in any major, with a background in mathematics and statistics areencouraged to apply. In general, three semesters of full time study, normally four courses per semester, arerequired to complete the MS degree, although it is possible for a student with a strong background to finish in oneyear. A student holding an assistantship, or who is otherwise prevented from carrying a full load of graduate work,generally requires an additional semester to finish.

Structure of the Master’s Program:

Depending on a student’s background, he or she should take eight (8) to ten (10) 3-credit courses, with thefollowing ones being required: STAT 5585, 5685, 5505, 5605, 5725 and 5515. In addition, the 1-credit seminarcourse STAT 5099 is required. The elective courses normally consist of four (4) additional courses, two to three inthe Department of Statistics and at least one in an area of application from other departments. Choices are madewith the approval of the candidate’s major and associate advisors. Up to 6 credits may be transferred subject to theapproval of the Department, provided that the student has taken equivalent graduate level courses that have notbeen counted towards any academic degree. After taking all required 3-credit courses, the student must take andpass a Master’s Examination. He or she must also demonstrate proficiency in statistical computing. There is nothesis requirement for the Master’s Degree.

Two Semester Plan (Knowledge of Statistics 5585-5685 and some applied statistics is assumed.)Statistics 5505, Statistics 5725, 2 Elective or Area of Application CoursesStatistics 5099, Statistics 5605, Statistics 5515, 2 Elective or Area of Application Courses

Three Semester PlanStatistics 5585, Statistics 5505, 1 Elective CourseStatistics 5685, Statistics 5515, Statistics 5605, 1 Elective CourseStatistics 5725, 2 Elective or Area of Application Courses, Statistics 5099 (1 credit)

Four Semester PlanStatistics 5585, Statistics 5505, 1 Elective CourseStatistics 5685, Statistics 5515, 1 Elective CourseStatistics 5725, 1 or 2 Elective or Area of Application CoursesStatistics 5605, 1 or 2 Elective or Area of Application Courses, Statistics 5099 (1 credit)

6

Notes:

STAT 5099 can only be registered for once. It may be taken during a summer or regular semester for part-time internship (1 credit) or full-time internship (3 credits).

In order to switch to the Ph.D. program or to be considered for financial support, a M.S. student must firstpass both parts of the Ph.D. Qualifying Exam at Ph.D. level. For international students, in order to be considered forfinancial support, passing UConn’s English Speak Test is also required.

Individuals who would like to concentrate on biostatistics are encouraged to apply to the ProfessionalMaster’s Program in Biostatistics of the Department.

International students must consult with UConn International Student & Scholar Services for visa rules and university requirements.

Professional Master's Degree in Biostatistics

The new professional MS program in Biostatistics will focus on practical skills that are sought after in health relatedfields, including pharmaceutical sciences and genomics. The objective of the program is to provide rigorous trainingin the modern areas of biostatistics related to the theory and application of statistical science to solve problems inpublic health, health services, health policy, and biomedical research, and other areas such as environmental healthand ecology. Students completing this program successfully will acquire expertise in topics including statisticalinference, linear regression, analysis of variance, design and analysis of clinical trials and epidemiological studies,programming in SAS and R, and consulting.

Individuals with a Bachelor’s degree in any major, with a background in mathematics and statistics are encouragedto apply. The program requires 31 credits and passing a written qualifying exam on both theoretical and appliedaspects of biostatistics. Qualified full time students are expected to complete this program in three to foursemesters.

Structure of the Master of Biostatistics Program:

A student should take at least ten (10) 3-credit courses and the 1-credit seminar/intern course STAT 5099. The following nine (9) courses are required:

BIST 5099. Investigation of Special Topics, Student SeminarBIST 5505. Applied Statistics IBIST 5605. Applied Statistics IIBIST 5515. Design of ExperimentBIST 5585. Mathematical Statistics IBIST 5685. Mathematical Statistics IIBIST 5625. Introduction to BiostatisticsBIST 6494. Data Management and Programming in SAS and RBIST 6494. Statistical Consulting

7

Two (2) elective courses should be chosen from the following courses, with one of them required to be BIST 5635 Clinical Trial, BIST 5645 Survival Analysis, or BIST 6494 Epidemiology:

BIST 5635. Clinical TrialBIST 5645. Survival AnalysisBIST 6494. EpidemiologyBIST 3965. Elementary Stochastic ProcessesBIST 4875. Nonparametric MethodsBIST 5361. Statistical ComputingBIST 5525. Sampling TheoryBIST 5665. Applied Multivariate AnalysisBIST 5725. Linear Models IBIST 5825. Applied Time SeriesBIST 6494. Applied Bayesian Data AnalysisBIST 6494. Bioinformatics IBIST 6494. Bioinformatics IIBIST 6494. Categorical Data AnalysisBIST 6494. Longitudinal Data AnalysisBIST 6494. Environmental Statistics

Choices of elective courses are made with the approval of the candidate’s major and associate advisors. Up to 6credits may be transferred subject to the approval of the Department, provided that the student has takenequivalent graduate level courses that have not been counted towards any academic degree. After taking allrequired 3-credit courses, the student must pass a written qualifying exam on both theoretical and applied aspectsof biostatistics. There is no thesis requirement.

Depending on how long a student plans to take to complete the Master’s program, the following are recommendedsequences of courses.

Three Semester plan BIST 5505, BIST 5585, BIST 5625, BIST 6494 (Data Management and Programming in SAS and R)

BIST 5515, BIST 5605, BIST 5685, BIST 5099 or Elective BIST 6494 (Statistical Consulting), BIST 5099 or Elective, 1 Elective course

Four Semester plan BIST 5505, BIST 5585, BIST 5625 BIST 5605, BIST 5515, 1 Elective course BIST 6494 (Data Management and Programming in SAS and R), BIST 5099 or Elective, 1 Elective course BIST 5685, BIST 6494 (Statistical Consulting), BIST 5099 or Elective

Notes:

STAT 5099 can only be registered for once. It may be taken during a summer or regular semester for part-time internship (1 credit) or full-time internship (3 credits).

International students must consult with UCONN International Student & Scholar Services for visa rules and university requirements.

8

The Faculty and their Research

Haim Bar, Assistant Professor, High dimensional data, bioinformatics, statistical modeling, model selection.

Kun Chen, Assistant Professor, Dimension Reduction, Variable Selection, Multivariate Analysis, StatisticalComputing, Statistical Ecology, Environmental Statistics, Bioinformatics, and Public Health Applications.

Ming-Hui Chen, Professor, Bayesian Statistical Methodology, Bayesian Computation, Bayesian Phylogenetics,Categorical Data Analysis, Design of Bayesian Clinical Trials, DNA Microarray Data Analysis, Meta-analysis, MissingData Analysis (EM, MCEM, and Bayesian), Monte Carlo Methodology, Prior Elicitation, Statistical Methodology andAnalysis for Prostate Cancer Data, Statistical Modeling, Survival Data Analysis, and Variable Selection.

Zhiyi Chi, Professor, Associate Department Head and Director of Graduate Studies, Applied Probability, StochasticProcesses, Large Deviations.

Dipak K. Dey, Board of Trustees Distinguished Professor and Associate Dean, CLAS, Bayesian Modeling, Big DataAnalytics, Categorical Data Analysis, Computational Statistics, Decision Theory, Dynamic Modeling Econometrics,Environmetrics, Multivariate Analysis, Psychometry, Reliability and Survival Analysis, Spatial Statistics, StatisticalGenetics, Statistical Image and Shape Analysis.

Joseph Glaz, Professor and Department Head, Applied probability, geometrical probability, probabilityapproximations, probability inequalities, parametric bootstrap, sequential analysis, simultaneous inference.

Ofer Harel, Professor, Methods for Handling Incomplete Data, Diagnostic Accuracy, Longitudinal Studies, BayesianMethods, Sampling Techniques, Mixture Models, Latent Class and Latent Transition Analysis, Statistical Consulting,Biostatistics, HIV Prevention and Public Health Applications.

Lynn Kuo, Professor, Bioinformatics and Biostatistics, Bayesian Computation, Bayesian Phylogenetics, SurvivalAnalysis, Nonparametric Bayesian Statistics, Software Reliability, Longitudinal Data Analysis, Survey Sampling.

Suman Majumdar, Associate Professor (Stamford Campus). Metrization of Weak Convergence, posteriorasymptotics, psychometry, inference in SDEs.

Nitis Mukhopadhyay, Professor, Applied Probability, Clinical Trial, Environmental Sampling, Multiple Comparisons,Multivariate Analysis, Selection and Ranking, Sequential Analysis, Simultaneous Inference.

Vladimir Pozdnyakov, Professor (Hartford Campus) and Director of Graduate Admissions. Limit Theorems,Sequential Analysis, Mathematical Finance, Occurrence of Patterns.

9

Nalini Ravishanker, Professor and Director of Undergraduate Program, Time Series modeling; Times-to-eventsAnalysis; Inference for Stable Processes; Signal Processing; Simultaneous Inference Procedures; Statistical Methodsin Actuarial Science, Marketing, Environmental Engineering and Transportation Engineering.

Elizabeth Schifano, Assistant Professor, Biostatistics, Statistical Genomics, High-dimensional Data Analysis, VariableSelection.

Rick Vitale, Professor, Convex-geometric methods in probability and statistics, stochastic geometry, inequalities.

Xiaojing Wang, Assistant Professor, Bayesian Modeling, Latent Variable Models and Item Response Models, StateSpace Models and Time Series Data Analysis, Gaussian Processes, Subgroup Analysis and Model Selection.

Jun Yan, Professor, Dynamic Survival Models, Clustered Data, Multivariate Dependence, Spatial Extremes,Estimating Functions, Statistical Computing, and Applications in Economics, Public Health, and EnvironmentalSciences.

Yuping Zhang, Assistant Professor, Research interests lie in development and application of statistical and computational methods to address scientific problems in genomics, systems biology, and complex diseases. Statistical Learning and Inference, High-dimensional Correlated Data Analysis, Graphical Models, Network Analysis.

10

Statistics Faculty with Joint Appointments

Rick Vitale, Professor. Joint Appointment with Mathematics Department.

Joint Appointments

Robert H. Aseltine, Jr., Professor. Joint Appointment with Division of Behavioral Sciences and Community Health – UConn Health, Deputy Director of Center for Public Health and Health Policy

Kent Holsinger, Board of Trustees Distinguished Professor, Vice Provost for Graduate Education and Dean of the Graduate School, Joint Appointment with Ecology and Evolutionary Biology

Tania B. Huedo-Medina, Assistant Professor, Joint Appointment with Allied Health Science

Paul Lewis, Professor, Joint Appointment with Ecology and Evolutionary Biology Department

Stephen Walsh, Associate Professor, Joint Appointment with Nursing Instruction and Research

Michael Willig, Professor, Joint Appointment with Ecology and Evolutionary BiologyDirector of the Center for Environmental Sciences and Engineering

Selected Faculty Publications

Haim Bar

(With Booth, James G., and Wells, Martin T.), 2014. A Bivariate Model for Simultaneous Testing in Bioinformatics Data. Journal of the American Statistical Association, Vol. 109, No. 506, Applications and Case Studies.

(With Lillard, D.), June 2012. Accounting for Heaping in Retrospectively Reported Event Data - A Mixture Model Approach. Statistics in Medicine

(With Schifano, E. D.), February 2011. Empirical and fully Bayesian approaches for random effects models in microarray data analysis. Statistical Modelling 11(1):71-88.

(With Booth J., Schifano, E. D. and Wells, M. T.) 2010. Laplace Approximated EM Microarray Analysis: An Empirical

11

Bayes Approach for Comparative Microarray Experiments. Statistical Science, 25(3):388-407

Kun Chen

(With Mukherjee, A., Wang, N. and Zhu, J.) 2015. On the degrees of freedom of reduced-rank estimators in multivariate regression. Biometrika, 102 (2): 457-477.

(With Yu, C. and Yao, W.) 2015. Outlier detection and robust mixture modeling using nonconvex penalized likelihood. Journal of Statistical Planning and Inference, 164, 27-38.

(With Chan, K.S. and Stenseth, N.C.) 2014. Source-sink reconstruction through regularized multi-component regression analysis---with application to assessing whether North Sea cod larvae contributed to local fjord cod in Skagerrak. Journal of the American Statistical Association. 109 (506), 560-573.

(With Ciannelli, L., Decker, M.B., Ladd, et al.) 2014. Reconstructing source-sink dynamics in a population with a pelagic dispersal phase. PLoS ONE, 9(5): e95316.

Ming-Hui Chen

(With Yao, H., Kim, S., Ibrahim, J.G., Shah, A.K., and Lin, J.) 2015. Bayesian Inference for Multivariate Meta-regression with Partially Observed Within-Study Sample Covariance Matrix. Journal of the American Statistical Association, 110(510), 528-544.

(With de Castro, M. and Zhang, Y.) 2015. Bayesian Path Specific Frailty Models for Multi-state Survival Data with Applications. Biometrics. DOI: 10.1111/biom.12298.

(With Zhang, D., Ibrahim, J. G., Boye, M. E., Wang, P., and Shen, W.) 2014. Assessing model fit in joint models of longitudinal and survival data with applications to cancer clinical trials. Statistics in Medicine, 33(27), 4715-4733.

(With Ibrahim, J.G., Zeng, D., Hu, K., and Jia, C.) 2014. Bayesian Design of Superiority Clinical Trials for Recurrent Events Data with Applications to Bleeding and Transfusion Events in Myelodyplastic Syndrome. Biometrics, 70, 1003-1013. DOI: 10.1111/biom.12215.

Zhiyi Chi

2015. Strong renewal theorems with infinite mean beyond local large deviations. Ann. Appl. Probab. 25, 1513--1539.

(With A. Sinha and M.-H. Chen) 2015. Bayesian inference of hidden Gamma process Cox model for survival data with ties. Statist. Sinica. In press. doi:10.5705/ss.2012.351.

2014. Nonnormal small jump approximation of infinitely divisible distributions. Adv. in Appl. Probab. 46, 963--984.

2012. On exact sampling of nonnegative infinitely divisible random variables. Adv. in Appl. Probab. 44, 842--873.

12

Dipak K. Dey

(With W. Li, C. Zhang, M. Willig, G. Wang and L. You) 2015. Bayesian Markov Chain Random Field Cosimulationfor Improving Land Cover Classification Accuracy. Mathematical Geoscience, 47, 2, 123-148.

(With R. Liu, A. Anand and B. Javidi) 2014. An entropy based clustering of embryonic stem cell using digital holographic microscopy. Journal of Optical Society of America. Series A, 31, 4, 677-684.

(With G. Goh) 2014. Bayesian Model Diagnostics using Functional Bregman Divergence. Journal of Multivariate Analysis, 124, 371-383.

(With X. Jiang, R. Pruneir, A. Wilson and K. Holsinger) 2013. A new class flexible link functions with application to species co-occurrence in cape floristic region. Annals of Applied Statistics, 7, 4, 1837- 2457.

Joseph Glaz

(With T.-L. Wu) 2015. A new adaptive procedure for multiple window scan statistics. Computational Statistics and Data Analysis 82, 164-172.

(With J. Chen) 2015. Scan statistics for monitoring data modeled by a negative binomial distribution. Communications in Statistics-Theory and Methods Ser. A. (in press).

(With J. Chen and C. P. Sison) 2015. Monte Carlo tests for multinomial proportions. Communications in Statistics-Theory and Methods Ser. A. (in press).

(With X. Wang and B. Zhao) 2014. A multiple window scan statistic for time series data. Statistics and Probability Letters 94, 196-203.

Ofer Harel

(With Chaurasia, A.) 2015. Partial F-tests with multiply imputed data in the linear regression framework viacoefficient of determination. Statistics in Medicine, 34(3), 432–443.

(With Chung, H. and Miglioretti, D.) 2013. Latent class regression: inference and estimation with two-stage multipleimputation” Biometrical Journal, 55(4), 541-553.

(With Boyko, J.) 2013. Missing data: Should we care? The American Journal of Public Health, 103(2), 200-201.

(With Siddique, J. and Crespi, C.M.) 2012. Addressing missing data mechanism uncertainty using multiple-modelmultiple imputation: application to a longitudinal clinical trial, Annals of Applied Statistics, 6(4), 1814-1837.

13

Lynn Kuo

(With P.O. Lewis, W. Xie, M.H. Chen and Y. Fan) Posterior Predictive Bayesian Phylogenetic Model Selection, Systematic Biology 2014; 63(3), 309-321

(With R. Wu, M.H. Chen, and P.O. Lewis) A New Method for Tracking Configuration for Dirichlet Process Sampling, Sri Lankan Journal of Applied Statistics, Special Issue: Modern Statistical Methodologies in the Cutting Edge of Science.2014, Dec. 1-24.

(With Z. Wei) Combining P Values for Gene Set Analysis, in Applied Statistics in Biomedicine and Clinical Trials Design: Selected Papers from 2013 ICSA/ISBS Joint Statistical Meetings, Eds: Zhen Chen, Aiyi Liu, Yongming Qu, Larry Tang, Naitee Ting, Yi Tsong, Springer, 2014, 495-518.

(With Z. Wei) Nonparametric Bayesian Functional Clustering for Time-Course Microarray Data, Statistics and Its Interface, V. 7, 2014, 543-557.

Suman Majumdar

2007. Uniform L1 posterior consistency in compact Gaussian shift experiments. Journal of Statistical Planning andInference, 137, 2102-2114.

Nitis Mukhopadhyay

2010. On a new sharper lower bound for a percentile of a Student’s t distribution with an application. Methodologyand Computing in Applied Probability, 12, 609-622.

(With A. Gut) 2010. On asymptotic and strict monotonicity of a sharper lower bound for Student’s t percentiles.Methodology and Computing in Applied Probability, 12, 647-657.

2010. A convolution identity and more with illustrations. Statistics and Probability Letters, 80, 1980-1984.

2011. On sharp Jensen’s inequality and some unusual applications. Communications in Statistics, Theory &Methods, 40, 1283-1297.

Vladimir Pozdnyakov

(with T. Meyer, Y. Wang, and J. Yan) On Modeling Animal Movements Using Brownian Motion with Measurement Error, Ecology, 95 (2014), 247-253.

(with K. Bharath and D. Dey) Asymptotics of the Empirical Cross-over Function, Annals of the Institute of Statistical Mathematics, 66 (2014), 369-382.

(with J.M. Steele) A Systematic Martingale Construction with Applications to Permutation Inequalities, Journal of Mathematical Analysis and Applications, 407 (2013), 130-140.

14

(with K. Bharath and D. Dey) Asymptotics of a Clustering Criterion for Smooth Distributions, Electronic Journal of Statistics, 7 (2013), 1078-1093.

Nalini Ravishanker

(With J. P. Nolan) 2009. Simultaneous prediction intervals for ARMA processes with stable innovations. Journal ofForecasting, 28, 235-246.

(With Jeffrey S. Pai) 2009. A multivariate preconditioned conjugate gradient approach for maximum likelihoodestimation in vector long memory processes. Statistics and Probability Letters, 79(9), 1282-1289.

(With Jeffrey S. Pai) 2010. Fast Bayesian estimation for VARFIMA processes with stable errors. Journal of StatisticalTheory and Practice, special volume edited by C.R. Rao and Sat Gupta, 4(4), 663-677.

(With H. Zhou, J. N. Ivan and A. W. Sadek) 2010. Safety effects of exclusive left-turn lanes at unsignalizedintersections and driveways. Journal of Transportation Safety & Security, 2(3), 221-229.

Elizabeth Schifano

(With M.P. Epstein, L.F. Bielak, M.A. Jhun, S.L.R Kardia, P.A. Peyser, and X. Lin) 2012. SNP Set Association Analysis forFamilial Data. Genetic Epidemiology. 36, 797-810.

(With L. Li, D.C. Christiani, and X. Lin) 2013. Genome-wide Association Analysis for Multiple Continuous SecondaryPhenotypes. American Journal of Human Genetics. 92(5), 744-759.

(With R.L. Strawderman and M.T. Wells) 2013. Hierarchical Bayes, Maximum a Posteriori Estimators, and MinimaxConcave Penalized Likelihood Estimation. Electronic Journal of Statistics. 7, 973-990.

Rick Vitale

2008. On the Gaussian representation of intrinsic volumes. Statistics and Probability Letters, 78, 1246–1249.

(With Y. Wang) 2008. The Wills functional for Gaussian processes. Statistics and Probability Letters, 78, 2181–2187.

2010 Convex bodies and Gaussian processes. Image Analysis and Stereology, 29, 13-19.

(With D. Fresen) 2014. Concentration of random polytopes around the expected convex hull. Electronic Communications in Probability, 19, no. 59m 1—8.

Xiaojing Wang

15

Jun Yan

(With Y. Cheng, J.P. Fine and H.-C. Lai) 2010. Uncovering symptom progression history from disease registry datawith application to young cystic fibrosis patients. Biometrics, 66(2): 594–602.

(With M.O. Prates, D.K. Dey and M.R. Willig) 2011. Intervention analysis of the hurricane impact on snailabundance in a tropical forest with spatio-temporal data. Journal of Agricultural, Biological, and EcologicalStatistics, 16(1): 142–156.

(With I. Kojadinovic and M. Holmes) 2011. Fast large-sample goodness-of-fit for copulas. Statistica Sinica,21(2):841–871.

(With C. Genest, I. Kojadinovic and J. Neslehov´a) 2011. A goodness-of-fit test for bivariate extreme value copulas.Bernoulli, 17(1): 253-275.

Yuping Zhang

(With R. Davis) 2013. Principal trend analysis for time-course data with applications in genomic medicine. The Annals of Applied Statistics, 7(4), 2205-2228.

(With R. Tibshirani, R. Davis) 2013. Classification of patients from time-course gene expression. Biostatistics, 14(1), 87-98.

(With J. Hardee, Z. Ouyang, A. Kundaje, P. Lacroute and M. Snyder) 2013. STAT3 targets suggest mechanisms of aggressive tumorigenesis in diffuse large B-cell lymphoma. G3: Genes Genomes Genetics, 3(12), 2173-2185.

(With R. Tibshirani and R. Davis) 2010. Predicting patient survival from longitudinal gene expression. Statistical Applications in Genetics and Molecular Biology, 9(1).

Published Books

Ming-Hui Chen

(With J.D. Petruccelli and B. Nandram) 1999. Applied Statistics for Engineers. Text Book, Prentice-Hall, Inc., ISBN 0-13-565953-1.

(With Q.-M. Shao and J.G. Ibrahim) 2000. Monte Carlo Methods in Bayesian Computation. Springer-Verlag, ISBN 0-387-98935-8.

(With J.G. Ibrahim and D. Sinha) 2001. Bayesian Survival Analysis. Springer-Verlag, ISBN 0-387-95277-2.

16

(With D.K. Dey, P. Mueller, D. Sun, and K. Ye) 2010. Frontiers of Statistical Decision Making and Bayesian Analysis. ---In Honor of James O. Berger. Springer-Verlag. ISBN 978-1-4419-6943-9.

(With L. Kuo and P.O. Lewis) 2014. Bayesian Phylogenetics: Methods, Algorithms, and Applications.Chapman & Hall/CRC Mathematical and Computational Biology. ISBN: 978-1466500792.

Dipak K. Dey

(With P. Mueller and D. Sinha), 1999. Practical Nonparametric and Semiparametric Bayesian Statistics. Springer-Verlag Lecture Notes Series, Volume 133.

(With S. K. Ghosh and B.K. Mallick), 2001. Generalized Linear Models: A Bayesian Perspective. Marcel-Dekker, Inc.

(With N. Ravishanker), 2002. A First Course for Linear Models. Chapman and Hall CRC.(With C.R. Rao), 2005. Handbook of Statistics Vol.25, Bayesian Thinking, Modeling and Computation, Elsevier Science, Amsterdam.

(With U. Singh and S.K. Upadhyay, Eds.) 2006. Bayesian Statistics and its Application. Proceedings of the International conference on Bayesian Statistics, Varanasi, India.

(With S. Ghosh and B.K. Mallick) 2010. Bayesian Bioinformatics. Chapman & Hall CRC).

(With M.-H. Chen, P. Müller, D. Sun and K. Ye) 2010. Frontiers of Statistical Decision Making and Bayesian Analysis --- InHonor of James O. Berger.

(With S. K. Upadhyay, U. Singh and A. Loganathan, Eds.) 2015. Current Trends in Bayesian Methodology with Applications.Chapman & HallCRC.

Joseph Glaz

(With N. Balakrishnan, Eds.) 1999. Recent Advances on Scan Statistics. Birkhauser Publishers, Boston.

(With J. Naus and S. Wallenstein) 2001. Scan Statistics. Springer, New York.

(With R. Baeza-Yates, J. Gzyl, J. Hüsler and J.L. Palacios, Eds.) 2005. Recent Advances in Applied Probability. Springer,New York.

(With J. Chiquet, N. Limnios and P. Moyal, Eds.) 2008. Book of Abstracts. IWAP 2008, 4th International Workshop inApplied Probability, Université de Technologie de Compiègne, Compiègne, France.

17

(With V. Pozdnyakov and S. Wallenstein, Eds.) 2009. Scan Statistics: Methods and Applications. Birkhauser, Boston.

(With M.V. Koutras, Eds.) 2010. Handbook on Scan Statistics. Springer (in preparation).

Lynn Kuo

(With M.H. Chen and P. O. Lewis, Eds.) 2014. Bayesian Phylogenetics: Methods, Algorithms, and Applications. Chapman & Hall/CRC Mathematical and Computational Biology. ISBN: 978-1466500792.

Ofer Harel

2009. Strategies for Data Analysis with Two Types of Missing Values: From Theory to Application. Lambert AcademicPublishing.

Nitis Mukhopadhyay

2000. Probability and Statistical Inference (ISBN #0-8247-0379-0). Marcel Dekker (Taylor & Francis Group).

(With S. Datta and S. Chattopadhyay) 2004. Applied Sequential Methodologies (ISBN #0-8247-5395-X). MarcelDekker (Taylor & Francis Group).

2006. Introductory Statistical Inference (ISBN #13:978-1-57444-613-5). Marcel Dekker (Taylor & Francis Group).

(With Basil M. de Silva) 2009. Sequential Methods and Their Applications (ISBN #13:978-1-58488-102-5). Chapman& Hall/CRC.

Nalini Ravishanker

(With D.K. Dey) 2002. A First Course in Linear Model Theory. Chapman Hall, CRC.

Recent Ph.D. GraduatesStudent Dissertation Current AffiliationJeff Stratton, 2011 Diagnostic Accuracy of a Binary

Test in the Presence of Two Types of Missing Values

Pratt & Whitney

Marcos Prates, 2011 A General Class of Link Functionwith Application to Spatio and Spatio-Temporal Data

Federal University of Minas GeraisBelo Horizonte, Brazil

Sandra Hurtado-Rua, 2011 A New Class of Bayesian Survival Models and Beyond

Cleveland State University

Gregory Matthews, 2011 Selected Topics of Statistical Loyola University18

Disclosure LimitationDebanjan Bhattacharjee, 2011 Statistical Inference for a

Normal Distribution with Variance as a Multiple of It’s Mean

Utah Valley University

Xiaojing Wang, 2011 Edynamic Regression Models for Interval Censored and PanelCount Survival Data

Google

Miaomiao Ge, 2011 Bayesian Modeling and Inference of Survival Data with Competing Risks

Boehringer-Ingelheim

Arijit Sinha, 2011 Bayesian Inference of Survival Data with Gamma Process Priors

Novartis

Karthik Bharath, 2012 On Inference for Discretely Observed Processes

University of Nottingham, UK

Bhargab Chattopadhyay, 2012 Performance of U-Statistics Having Kernels of Degree Higher Than Two in Inference Problems with Applications

University of Texas, Dallas

Shan Hu, 2012 Dynamic Modeling of Discrete-valued Time Series, with Applications

Plymouth Rock Assurance

Wenqing Li, 2012 Bayesian Design of Non-Inferiority Clinical Trials

Novartis, NJ

Ran Liu, 2012 Segmentation, Classification and Tracking of 3-D Images using Bayesian Methods

Merck & Co.

Ziwen Wei, 2012 On Applications of Bayesian Methodologies in Bioinformatics and Biostatistics

Merck & Co.

Rui Wu, 2012 New Developments on Estimating Posterior Marginal Density and Dirichlet Process with Applications

Novartis

Hui Yao, 2012 Bayesian Modeling and Inference for Meta Data

Ernst & Young

Yuanye Zhang, 2012 Bayesian Modeling and Inference of Survival Data with Semi-Competing Risks

Novartis

Sy Han (Steven) Chiou, 2013 Statistical Methods and Computing for Semiparametric Accelerated Failure Time Modelwith Induced Smoothing

University of Minnesota, Duluth

Xun (Tony) Jiang, 2013 A New Class of Link Functions for Modeling Categorical Data

Amgen

19

with Applications in BiologyJennifer Boyko, 2013 Handling Data with Three Types

of Missing ValuesBoehringer-Ingelheim

Gong-Yi Liao, 2013 Residual Likelihood Based Clustering Models

Northern Trust Company

Sankha Perera, 2013 Multiple Crossing Fixed-Size Sequential Confidence Regions for the Mean Vector and Regression Parameters Under Multivariate Normality

Plymouth Rock Assurance

Ashok Chaurasia, 2013 Model Selection Procedures forIncomplete Data

National Institute of Health

Xiao (Leo) Wang, 2013 Scan Statistics for Normal Data Barclays Investment BankSairam Rayaprolu, 2013 Multiple Testing Under

Dependence with Approximate Posterior Likelihood

Disney

Hongwei Shang, 2013 A Two-Step Estimation Procedure and a Goodness-of-Fit Test for Spatial Extremes Models

Hewlett Packard Labs

Swarnali Banerjee, 2014 Sequential Fixed-Accuracy Confidence Interval Estimation Methodologies in Statistical Ecology and Related Topics

Old Dominion University

Valerie Pare, 2014 Impact of Prior Distribution Uncertainty in Multiple Imputation Inference

Wesleyan University

Danjie Zhang, 2014 Model Assessment in Joint Modeling of Longitudinal and Survival Data with Applications to Cancer Clinical Trials

Gilead Sciences, Inc.

Patrick Harrington, 2015 Classification and Multiple Hypothesis Testing in Microarray and RNA-Seq Experiments

Genomic Health, Inc.

Bo Zhao, 2015 Scan Statistics for Detecting a Local Change in Variance for Normal Data

Travelers Insurance

Chantal Larose, 2015 Model Based Clustering of Incomplete Data

The State University of New York, New Paltz

Gyuhyeong Goh, 2015 Applications of Bregman Divergence Measures in Bayesian Modeling

Kansas State University, Manhattan

20

Graduate Course List

STAT 5005 Introduction to Applied Statistics One-, two- and k-sample problems, regression, elementary factorialand repeated measures designs, covariance. Use of computer packages, e.g., SAS and MINITAB. Prerequisite: Notopen to students who have passed STAT 201 or STAT 2215Q.

STAT 5015 Distribution Theory for Statistics Open to graduate students in Statistics, others with permission.

STAT 5099 Investigation of Special Topics Topical seminar course. STAT 5105 Quantitative Methods in the Behavioral Sciences. A course designed to acquaint the student with theapplication of statistical methods in the behavioral sciences. Correlational methods include multiple regression andrelated multivariate techniques.

STAT 5192 Supervised Research in Statistics Supervised Research

STAT 5315 Analysis of Experiments Straight-line regression, multiple regression, regression diagnostics,transformations, dummy variables, one-way and two-way analysis of variance, analysis of covariance, stepwiseregression. Prerequisite: STAT 5005. Not open to students who have passed STAT 242 or STAT 3115Q.

STAT 5361 Statistical Computing Use of computing for statistical problems; obtaining features of distributions, fittingmodels and implementing inference. Basic numerical methods, nonlinear statistical methods, numerical integration,modern simulation methods. Open to graduate students in Statistics, others with permission.

STAT 5415 Advanced Statistical Methods Discrete and continuous random variables, exponential family, joint andconditional distributions, order statistics, statistical inference, point estimation, confidence interval estimation, andhypothesis testing.

STAT 5505 Applied Statistics I Exploratory data analysis: stem-and leaf plots, Box-plots, symmetry plots, quantileplots, transformations, discrete and continuous distributions, goodness of fit tests, parametric and non-parametricinference for one sample and two sample problems, robust estimation, Monte Carlo inference, bootstrapping. Opento graduate students in Statistics, others with permission.

STAT 5515 Design of Experiments One way analysis of variance, multiple comparison of means, randomized blockdesigns, Latin and Graeco-Latin square designs, factorial designs, two-level factorial and fractional factorial designs,nested and hierarchical designs, split-plot designs. Prerequisite: STAT 5005. Not open to students who have passedSTAT 243 or STAT 3515Q.

STAT 5525 Sampling Theory Sampling and nonsampling error, bias, sampling design, simple random sampling,sampling with unequal probabilities, stratified sampling, optimum allocation, proportional allocation, ratioestimators, regression estimators, super population approaches, inference in finite populations. Open to graduatestudents in Statistics, others with permission.

STAT 5535 Introduction to Operations Research Open to graduate students in Statistics, others with permission.

21

STAT 5585 Mathematical Statistics I Introduction to probability theory, transformations and expectations, momentgenerating function, discrete and continuous distributions, joint and marginal distributions of random vectors,conditional distributions and independence, sums of random variables, order statistics, convergence of a sequenceof random variables, the central limit theorem.

STAT 5605 Applied Statistics II Analysis of variance, regression and correlation, analysis of covariance, general linearmodels, robust regression procedures, and regression diagnostics. Prerequisite: STAT 5505.

STAT 5625 Introduction to Biostatistics Rates and proportions, sensitivity, specificity, two-way tables, odds ratios,relative risk, ordered and non-ordered classifications, rends, case-control studies, elements of regression includinglogistic and Poisson, additivity and interaction, combination of studies and meta-analysis.

STAT 5635 Clinical Trials Basic concepts of clinical trial analysis; controls, randomization, blinding, surrogateendpoints, sample size calculations, sequential monitoring, side-effect evaluation and intention-to-treat analyses.Also, experimental designs including dose response study, multicenter trials, clinical trials for drug development,stratification, and cross-over trials.

STAT 5645 Concepts and Analysis of Survival Data Survival models, censoring and truncation, nonparametricestimation of survival functions, comparison of treatment groups, mathematical and graphical methods forassessing goodness of fit, parametric and nonparametric regression models.

STAT 5665 Applied Multivariate Analysis Multivariate normal distributions, inference about a mean vector,comparison of several multivariate means, principal components, factor analysis, canonical correlation analysis,discrimination and classification, cluster analysis. Open to graduate students in Statistics, others with permission.

STAT 5685 Mathematical Statistics II The sufficiency principle, the likelihood principle, the invariance principle, pointestimation, methods of evaluating point estimators, hypotheses testing, methods of evaluating tests, intervalestimation, methods of evaluating interval estimators. Prerequisite: STAT 5585.

STAT 5725 Linear Statistical Models Linear and matrix algebra concepts, generalized inverses of matrices,multivariate normal distribution, distributions of quadratic forms in normal random vectors, least squaresestimation for full rank and less than full rank linear models, estimation under linear restrictions, testing linearhypotheses. Open to graduate students in Statistics, others with permission.

STAT 5825 Applied Time Series Introduction to prediction using time-series regression methods with non-seasonaland seasonal data. Smoothing methods for forecasting. Modeling and forecasting using univariate autoregressivemoving average models. Open to graduate students in Statistics, others with permission.

STAT 6315 Statistical Inference I Exponential families, sufficient statistics, loss function, decision rules, convexity,prior information, unbiasedness, Bayesian analysis, minimaxity, admissibility, simultaneous and shrinkageestimation, invariance, equivariant estimation. Open to graduate students in Statistics, others with permission.

STAT 6325 Advanced Probability Fundamentals of measure and integration theory: fields, o-fields, and measures;extension of measures; Lebesgue-Stieltjes measures and distribution functions; measurable functions andintegration theorems; the Radon-Nikodym Theorem, product measures, and Fubini’s Theorem. Introduction tomeasure-theoretic probability: probability spaces and random variables; expectation and moments; independence,

22

conditioning, the Borel-Cantelli Lemmas, and other topics as time allows. Open to graduate students in Statistics,others with permission.

STAT 6425 Seminar in Applied Probability Open to graduate students in Statistics, others with permission.

STAT 6494 Seminar in Applied Statistics Open to graduate students in Statistics, others with permission.

STAT 6515 Statistical Inference II Statistics and subfields, conditional expectations and probability distributions,uniformly most powerful tests, uniformly most powerful unbiased tests, confidence sets, conditional inference,robustness, change point problems, order restricted inference, asymptotics of likelihood ratio tests. Open tograduate students in Statistics, others with permission. Prerequisite: STAT 6315.

STAT 6594 Seminar in Nonparametric Statistics Open to graduate students in Statistics, others with permission.

STAT 6625 Seminar in Biostatistics Open to graduate students in Statistics, others with permission.

STAT 6694 Seminar in Multivariate Statistics Open to graduate students in Statistics, others with permission.

STAT 6794 Seminar in the Theory of Statistical Inference Open to graduate students in Statistics, others withpermission.

STAT 6894 Seminar in the Theory of Probability and Stochastic Processes Open to graduate students in Statistics,others with permission.

******************************************************************************************

In addition, special topic courses are offered in areas such as: bioinformatics, categorical data analysis, time seriesmethods, generalized linear models, Bayesian data analysis, spatial and longitudinal data modeling, sequentialanalysis, stochastic geometry, survival analysis, approximations and inequalities, nonparametric methods, andadvanced topics in inference.

rev. 7.9.15

23