Genetic association studies often evaluate the combined group-wise effects of rare and common genetic variants on phenotypes at gene level. Many approaches have been proposed for group-wise association tests, such as the widely used burden tests and sequence kernel association tests with sequencing data. Most of these approaches focus on identifying mean effects. As the genetic associations are complex, we propose an efficient integrated rank test to investigate the genetic effect across the entire distribution/quantile function of a phenotype. The resulting test complements the mean-based analysis and improve efficiency and robustness. The proposed test integrates the rank score test statistics over quantile levels while incorporating Cauchy combination test scheme and Fisher’s method to maximize the power. It generalized the classical quantile-specific rank-score test. Using simulations studies and real Metabochip data on lipid traits, we investigated the performance of the new test in comparison with the burden tests and sequence kernel association tests in multiple scenarios. This is joint work with Tianying Wang and Iuliana Ionita-Laza.

Bio: Ying Wei is a statistician and a Professor of Biostatistics in the Columbia University Mailman School of Public Health, working primarily on quantile regression, semiparametric models of longitudinal data, and their applications.

Wei earned her Ph.D. in Statistics from the University of Illinois at Urbana–Champaign in 2004 and has been a faculty member of Biostatistics at Columbia University, and also an affiliated member of the Data Science Institute ever since.

In 2011, Wei received the Noether Young Scholar Award of the American Statistical Association, “for outstanding early contributions to nonparametric statistics.” In 2015, Wei was elected as a Fellow of the American Statistical Association. Wei is also an elected member of the International Statistical Institute. In 2020 she was named as a Fellow of the Institute of Mathematical Statistics “for contributions to the development, dissemination, and application of mathematical statistics”.

Event address for attendees:		https://uconn-cmr.webex.com/uconn-cmr/onstage/g.php?MTID=e6c6243ddbe5366041dad514f5a20ac48
Date and time:		Wednesday, September 9, 2020 4:00 pm Eastern Daylight Time (New York, GMT-04:00)
Duration:		1 hour

Expectation function-based decision and game theoretic models require both computation of the utility function and its optimization. This can be computationally challenging especially in cases with continuous and multi-modal sources of uncertainty or complex objective function surfaces. We propose augmented simulation approaches that treat the decision variable(s) as random and construct an augmented distribution in the space of both decisions and random variables. Simulation from this distribution simultaneously solves for the expectation of the objective function and optimization problem. In doing so, we sample more frequently from the marginal decision space in that the objective function has higher values in a maximization problem. This talk introduces augmented probability simulation and its extensions to solve for stochastic programming problems and game theoretic models. There will be a discussion and illustration on a variety of applications such as news-vendor type models, service systems and cybersecurity. 

Bio: Dr. Tahir Ekin is an Associate Professor of Quantitative Methods in McCoy College of Business, Texas State University. His research interests include analytical applications in health care fraud assessment and decision modeling under uncertainty. His book on health care fraud analytics titled “Statistics and Health Care Fraud: How to Save Billions” has been recently published. His work has appeared in a variety of journals including Journal of the Royal Statistical Society Series C, International Statistical Review, Naval Research Logistics and Decision Analysis among others. Dr. Ekin holds a Ph.D. in Decision Sciences from The George Washington University, and a B.S. in Industrial Engineering from Bilkent University, Turkey. He is an elected member of International Statistical Institute and currently serves as Vice President of the International Society of Business and Industrial Statisticians.

The Vector AutoRegressive Moving Average (VARMA) model is fundamental to the theory of multivariate time series; however, identifiability issues have led practitioners to abandon it in favor of the simpler but more restrictive Vector AutoRegressive (VAR) model. We narrow this gap with a new optimization-based approach to VARMA identification built upon the principle of parsimony. Among all equivalent data-generating models, we use convex optimization to seek the parameterization that is “simplest” in a certain sense. A user-specified strongly convex penalty is used to measure model simplicity, and that same penalty is then used to define an estimator that can be efficiently computed.  We establish consistency of our estimators in a double- asymptotic regime.  Our non-asymptotic error bound analysis accommodates both model specification and parameter estimation steps, a feature that is crucial for studying large-scale VARMA algorithms and is largely unexplored in existing literature.  Our analysis also provides new results on infinite-order VAR, elastic net estimation under a singular covariance structure of regressors, and new concentration inequalities for quadratic forms of random variables from Gaussian time series, which may be of independent interest.  We illustrate the advantage of our method over VAR alternatives on simulated and real data examples.

A Brownian motion whose infinitesimal variance alternates according to a telegraph process is considered. This stochastic process can be employed to model variety of real-word situations. In this work we applied our findings for animal movement analysis. The main goal is to develop an estimation procedure for underlying model parameters when the Brownian Motion governed by telegraph process is observed discretely. Resulting sequence of observations is not Markov. But since the location-state process is Markov, the likelihood estimation can be done with help of Hidden Markov Model tools. Further extensions of the model are discussed. More specifically, we consider (1) introducing an additional hidden state and (2) incorporating measurement errors into the model.  (joint work with Chaoran Hu, Mark Elbroch, Tom Meyer, and Jun Yan)

Much of the literature on estimating causal effects concerns discrete exposures. Recently, there has been increased interest in continuous exposures; that is, exposures that can take an uncountable number of values. Examples of such exposures include air pollution, pre-vaccination antibody responses, and concentrations of harmful chemicals in the blood. In this talk, I will provide an introduction to the area of causal inference with continuous exposures. I will then provide an overview of some of the recent research concerning nonparametric causal inference with continuous exposures, including my own recent and ongoing research. In particular, I will discuss approaches to nonparametric pointwise and global inference on causal dose-response curves, and, time permitting, inference on alternative causal parameters such as the effects of stochastic and incremental interventions.

The department of Statistics at the University of Connecticut is honored to announce the 25th Distinguished Statistician Colloquium. The Pfizer colloquium series ran from 1978 until 2012 and was renewed in 2018. The colloquium series featured C. R. Rao, Bradley Efron, D.R. Cox, Grace Wahba and many more. For a complete list, see https://stat.uconn.edu/pfizer-colloquium/. The purpose of the Colloquium is to provide a forum for a distinguished statistician to share and disseminate their unique perspective and work in the theory and/or application of statistics. Starting from 2018, the series has been co-sponsored by Pfizer, the American Statistical Association, and the Department of Statistics at the University of Connecticut. 

 

This year’s speaker at the 25th Pfizer Distinguished Statistician Series will be Professor Emerita Nan Laird from Harvard T.H. Chan School of Public Health. This year colloquium will be virtual and will take place on Wednesday, October 14^th, 2020 from 3:00-5:00pmEST. The interview will be conducted by Christoph Lange (Harvard T.H. Chan School of Public Health) and Joseph Hogan (Brown University). 

The lecture and the interview are open to the public but pre-registration will be needed for a link to the webcast.  The event registration website is:   https://uconnuecs.cvent.com/Pfizer2020   

 

If you have questions, please contact, Juliet Kapsis at juliet.kapsis@uconn.edu or conferences@uconn.edu. 

 

We thank Pfizer and the ASA for their generous financial support. We also thank the members of the selection committee – Dan Meyer and Demissie Alemayehu from Pfizer, Ron Wasserstein and Nancy Flournoy from the ASA, and Dipak Dey (Chair), Joseph Glaz and Ming-Hui Chen from UConn. Professor Chen also represents the New England Statistical Society (NESS). 

The analysis of tensor data has become an active research topic in this area of big data. Datasets in the form of tensors, or high-order matrices, arise from a wide range of applications, such as financial econometrics, genomics, and material science. In addition, tensor methods provide unique perspectives and solutions to many high-dimensional problems, such as topic modeling and high-order interaction pursuit, where the observations are not necessarily tensors. High-dimensional tensor problems generally possess distinct characteristics that pose unprecedented challenges to the data science community. There is a clear need to develop new methods, efficient algorithms, and fundamental theory to analyze the high-dimensional tensor data.

In this talk, we discuss some recent advances in high-dimensional tensor data analysis through the consideration of several fundamental and interrelated problems, including tensor SVD and tensor regression. We illustrate how we develop new statistically optimal methods and computationally efficient algorithms that exploit useful information from high-dimensional tensor data based on the modern theories of computation, high-dimensional statistics, and non-convex optimization.

In this talk we introduce Sequential Patient Recruit Monitoring (SPRM), a new and efficient accrual monitoring method. Built on a sequential probability ratio test using Woodroofe boundaries, SPRM is an evidence-based, decision-support tool that provides opportunity for corrective action in a timely manner. Suitable for the modern, centralized data management environment, it requires minimal effort to maintain. The method can easily accommodate protocol changes involving sample size and/or recruitment period modification.

We also propose Sequential Event Rate Monitoring (SERM), a new continuous monitoring method for the event rate of time-to-event data in a clinical trial. SERM gives an early warning if the target rate is unlikely to be achieved by the end of study. Since SERM is designed to monitor the overall event rate, blindness of the trial is preserved. If necessary, the method could suggest the number of extra recruitments required for the planned number of primary events. It can also be used to estimate an extension of the follow-up time. We illustrate the methods using data from a well-known Phase III clinical trial.

Bio: Dr. Kim is a mathematical statistician at the Office of Biostatistics Research within National Heart, Lung, and Blood Institute (NHLBI), Bethesda, Maryland. She received PhD in Statistics from the University of Michigan, Ann Arbor in 2003. Before joining NIH in 2013, she held a faculty position at Virginia Tech. Her research interests include: sequential methods in clinical trials, change-point inference, statistical genetics and bioinformatics. At NIH, she has been involved in large NHLBI-sponsored clinical trials and intramural projects, provided scientific reviews of protocols and expert opinions for these projects, and developed novel methodologies for applications in clinical trials. Also, Dr. Kim has years of experience in collaborative research in other areas including mobile health, bioengineering, health services, and environmental science.

Networks play important roles in elucidating biological systems and complex diseases. It is necessary to develop new methods for network learning and inference based on high-dimensional, heterogeneous and complex biological data generated by modern high-throughput biotechnologies. This talk will feature two new methodologies: 1) a statistical framework for joint learning of multiple heterogeneous exponential Markov Random Fields and its associated variational inference and theory, and 2) statistical inference of network disturbances leveraging topologies and multi-view biological data.