Announcement

– Chaoran Hu has received the 2020 Student Paper Award in the Statistical Computing and Statistical Graphics Sections of the ASA

We are pleased to inform you that Chaoran’s paper on animal movement has been selected as one of the winners of this year’s student paper competition from the Section on Statistical Computing and the Section on Statistical Graphics of ASA. The same paper has also been chosen as honorable mention for 2020 JSM ENVR section student paper competition award.

More info about the Award of ASA can be found at the following links: Click here

Congratulations!

– Zhe Sun has received 2020 ENAR Distinguished Student Paper Award and John Van Ryzin Award

We are delighted to report that Zhe’s manuscript entitled Sparse Log-Contrast Regression with Functional Compositional Predictors: Linking Gut Microbiome Trajectory in Early Postnatal Period to Neurobehavioral Development of Preterm Infants has been selected as the best paper submitted this year(2020) to the International Biometric Society Eastern North American Region’s (ENAR) Distinguished Student Paper Award Competition! This paper was co-authored by Zhe Sun, Wanli Xu, Xiaomei Cong, Gen Li and Kun Chen. This award for the top paper is called the John Van Ryzin Award, and is awarded to Zhe in addition to the Distinguished Student Paper Award.

This is an unprecedented achievement in the department of Statistics. Congratulations!

– Yan Li has received 2020 ENAR Distinguished Student Paper Award

We are happy to report that Yan Li has been selected to receive one of the International Biometric Society Eastern North American Region’s (ENAR) Distinguished Student Paper Awards for the 2020 ENAR Spring Meeting in Nashville, TN. He is co-advised by Dr. Jun Yan and Dr. Kun Chen. The award recognizes his paper entitled “Pursuing Sources of Heterogeneity in Mixture Regression”, co-authored by Yan Li, Chun Yu, Yize Zhao, Robert Aseltine, Weixin Yao and Kun Chen.

Once again, the quality of manuscripts submitted was high and the competition was keen. It was difficult for the committee to choose among so many deserving papers. Congratulations on his accomplishment!

– NESS Colloquium @ BU – Nov. 14 – David Dunson (Duke University) – Learning & Exploiting Low-dimensional Structure In High-Dimensional Data

Hi All,
The NESS Colloquium series will continue on Thursday, November 14th at Boston University with a talk Professor David Dunson from Duke University. This colloquium is open to the general public and should be accessible to those interested in statistics at all levels. The event is sponsored by the New England Statistics Society (NESS) and the Department of Mathematics and Statistics at Boston University.

Please share this email widely and please post the attached flyer. See below for more information.

Best,
Daniel Sussman
Assistant Professor, Department of Mathematics and Statistics
Boston University

When

Thursday, November 14, 2019
Starting at 4 pm (with refreshments served starting at 3:25 pm)

Where

College of General Studies Building
871 Commonwealth Avenue, Boston, MA, 02215
Room CGS 129

Who

Professor David Dunson is the Arts and Sciences Professor of Statistical Science at Duke University, has been given numerous awards including the COPSS Presidents’ Award, and is a Fellow in the Institute of Mathematical Statistics and the American Statistical Association.

Professor Dunson’s research spans numerous areas of statistics with a focus on scalable procedures with provable guarantees that can be applied to complex data structures. His work has had broad impact within the statistics community and in many other fields including biomedical research, genomics, ecology, criminal justice, and neuroscience.

What

Learning & Exploiting Low-dimensional Structure In High-Dimensional Data

This talk will focus on the problem of learning low-dimensional geometric structure in high-dimensional data. We allow the lower-dimensional subspace to be non-linear. There are a variety of algorithms available for “manifold learning” and non-linear dimensionality reduction, mostly relying on locally linear approximations and not providing a likelihood-based approach for inferences. We propose a new class of simple geometric dictionaries for characterizing the subspace, along with a simple optimization algorithm and a model-based approach to inference. We provide strong theory support, in terms of tight bounds on covering numbers, showing advantages of our approach relative to local linear dictionaries. These advantages are shown to carry over to practical performance in a variety of settings including manifold learning, manifold de-noising, data visualization (providing a competitor to the popular tSNE), classification (providing a competitor to deep neural networks that requires fewer training examples), and geodesic distance estimation. We additionally provide a Bayesian nonparametric methodology for inference, using a new class of kernels, which is shown to outperform current methods, such as mixtures of multivariate Gaussians.

– 2019 ASA CT Chapter Short Course “Borrowing from Historic Data in Clinical Trials” on Nov. 14

Dear all,

ASA CT Chapter is very pleased to offer the 2019 Short Course “Borrowing from Historical Data in Clinical Trials” by Dr. Martin Oliver Sailer on Thursday, Nov. 14 (10am-3pm) at University of Connecticut Homer Babbidge Library 2nd Level. You may register for this course here (https://www.123signup.com/register?id=rbgzp).

The registration fees are $60 for ASA CT chapter members, $75 for non-members, and $30 for students.

Please see the attached flyer for more details about this event.

If you have any questions, please email ctchapterasa@gmail.com.

Thanks and we look forward to seeing you at this short course on Nov. 14!

Mary Zhao
Secretary, ASA CT Chapter

– UConn Hosts New Sports Analytics Symposium

UConn today
On Oct. 5, a university with a strong national academic reputation and a storied basketball program hosted a new conference on sports statistics, billed as the first of its kind to focus on the needs of students.

The UConn Sports Analytics Symposium brought undergraduate and graduate students together with academic and industry professionals to learn how to use data science to enhance modern sports.

“We wanted to have something where students can get their foot in the door and see all the opportunities involved in sports analytics,” says Taaj Cheema ’20 (CLAS) of Tolland, Connecticut.

A group photo of eight people
From left to right: Jun Yan, professor of statistics; Haim Bar, associate professor of statistics; Gregory Matthews ’11 Ph.D., assistant professor of mathematics and statistics and director for data science at Loyola University Chicago; Meredith J. Wills, a data scientist at SportsMEDIA Technology Corps; Taaj Cheema ’20 (CLAS), vice president of the UConn Data Science Club and a data science and molecular and cell biology major and economics minor; Peter Diplock, UConn assistant vice provost for excellence in teaching and learning; Jamelle Elliott ’96 (BUS), ’97 MA, associate athletic director for the UConn National ‘C’ Club; and Elizabeth Schifano, assistant professor of statistics. Diplock and Elliott delivered welcoming remarks at the symposium. (Photo courtesy Taaj Cheema)

The event featured keynote talks by Gregory Matthews ’11 Ph.D., assistant professor of mathematics and statistics and director for data science at Loyola University Chicago; Meredith J. Wills, a data scientist at SportsMEDIA Technology Corps; and Brian Macdonald, director of data analytics at ESPN.

The day-long program included introductory and advanced workshops on topics like R and Python programming languages, led by graduate students in the Department of Statistics. Students also presented their own research at a poster session.

Many of the about 130 student attendees came from UConn, with others traveling from Colorado State University, California State University, Fullerton, and even Saratoga High School in California.

The conference was hosted by UConn’s Statistical Data Science Lab in the Department of Statistics and the UConn Data Science Club, a student organization advised by faculty in the College of Liberal Arts and Sciences and School of Engineering.

Cheema, who is vice president of the UConn Data Science Club and an individualized major in data science, says he initially proposed the event to engage UConn’s growing population of students interested in the field of data science.

“UConn is a big sports school, and one of the most interesting applications for data analytics is in sports,” he says. “For students, a lot of opportunities can be out of reach. This event brings the opportunities right to UConn.”

Jun Yan, a professor of statistics and advisor to Cheema and the UConn Data Science Club, agrees that analytics of professional and fantasy sports often draw students to data science.

“Sports analytics are applications of data science that use available data to make better decisions across the whole spectrum of the sports business,” says Yan. “The analytics skills can of course be applied to other fields, but sports get many students interested in the first place.”

According to Matthews, the field of data science was just becoming a formalized academic discipline while he was a Ph.D. student at UConn less than a decade ago.

During that time, Matthews began writing about statistical topics in sports for his blog, Stats in the Wild.

Since then, Matthews says he’s seen the role of data analytics in sports grow significantly, with more teams and leagues looking to historical data to get a competitive advantage over opponents.

“Data science has already made a lasting impact on sports, from defensive shifts in baseball to the way basketball is played in the NBA–with the shifting reliance on the three-point shot,” he says. “I predict that the impacts will continue to grow in the decades to come.”

About a dozen other conferences focusing on sports analytics will take place this academic year in the U.S., among them the annual MIT Sloan Sports Analytics Conference in Boston. But Matthews, Yan, and Cheema all say these events can be very technical and can cost hundreds of dollars to attend.

“[UConn’s event] is a departure from many other high-profile sports analytics conferences, which generally focus on more advanced topics,” says Matthews. “Those conferences can be expensive, which is often a barrier to student attendance. Alternatively, this event is nearly free.”

Yan hopes to expand the event in the future so that students can use it as an opportunity to learn, network, and showcase their skills to industry representatives.

“Our faculty has expertise directly applicable to sports analytics,” says Yan. “In the future, as our impact grows, the conference will also provide a platform for the sports industry to recruit our students.”

The UConn Sports Analytics Symposium was sponsored by the Department of Statistics, Sport Management Program, Center for Population Health, and College of Liberal Arts and Sciences at UConn; ESPN; and the New York City Metropolitan Area Chapter and the Statistics in Sports Section of the American Statistical Association.