Conference Schedule

Keynote Speaker

Dr. Mahlet Tadesse, Professor | Chair, Department of Mathematics & Statistics- Georgetown University

Talk: Identifying cluster structure and relevant features in high-dimensional data

Abstract: High-dimensional data often have latent cluster structure. A large proportion of the measured features tend to be noise and obscure this structure. Feature selection is therefore not only a matter of parsimony but a necessity, in order to uncover the cluster structure and identify component-specific relevant features. I will present some of the methods we have proposed to address this problem by combining ideas of mixture of regression models, variable selection, and stochastic partitioning methods. I will conclude with a brief discussion on connections with AI models.

Dr. Mahlet Tadesse is Professor and Chair in the Department of Mathematics and Statistics at Georgetown University. Her research focuses on the development of statistical and computational tools for the analysis of large-scale genomic data. She is particularly interested in stochastic search methods and Bayesian inferential strategies to identify structures and relationships in high-dimensional data sets. She is an elected member of the International Statistical Institute (since 2006) and an elected fellow of the American Statistical Association (since 2013).

Opening Remarks

Dr. Purna Gamage is Program Director, Associate Teaching Professor of Data Science and Analytics Master’s program at Georgetown University. Dr. Purna also serves as a member of the Graduate Executive Committee (“Grad ExCo”),  Executive Council and Executive Board of the Honor Council at Georgetown University. Having previously worked at Texas Tech University and Wake Forest University, she brings a wealth of experience to her role. Dr. Purna received her PhD in Mathematics majoring in Statistics in 2018 and Master’s Degree in Statistics from Texas Tech University for her research in Bayesian Hierarchical Modeling, Spatial and Temporal Data Analysis, and Ecological Statistics. Dr. Purna’s research is centered on leveraging Machine Learning models, Natural Language Processing (NLP), Deep Learning, LLMTime, Transformer based Models and Time Series analysis in various domains. Her current work involves exploring the comparative effectiveness of Traditional Time Series Modeling and Deep Learning Models on Stock Market dynamics; a comprehensive comparison of Time-LLMs and Traditional Financial Time Series Modeling to assess predictive power.

Industry Panel

Nathaniel Reynolds, Senior Data Analyst, Library of Congress

Nathaniel Reynolds is a senior data analyst at the Library of Congress, Federal Research Division. Nathaniel works on applied data analytics projects including survey analysis, financial modeling, interactive dashboards, and increasingly today, ramping up data preparedness for AI use. Nathaniel also teaches part-time as adjunct faculty for the Data Analytics and Computational Social Science (DACSS) program at his alma mater, the University of Massachusetts Amherst. Nathaniel is speaking in a personal capacity and not representing the Library of Congress or the federal government.

Amit Arora, Principal Solutions Architect, AWS

Amit Arora is a Principal Solutions Architect – AI/ML at AWS and an Adjunct Lecturer at Georgetown University. Previously, he was a data scientist at Hughes Network Systems.He is an experienced cloud architect and data science professional specializing in applied ML, data pipelines and deploying ML in production. As part of his current role at AWS he helps enterprise customers use cloud-based machine learning platforms and services to rapidly scale their innovations.

Michael Rossetti, ML Researcher, Google

Michael Rossetti is a data scientist, software engineer, and machine learning researcher at Google. He has worked as a polling data analyst for a winning US Presidential campaign, a data analytics director for a Silicon Valley startup, and a technology consultant for the US Government. He teaches courses in data science, computer science, and software development, and conducts research in applied machine learning. Michael is speaking in a personal capacity and not as a representative of Google.

Isfar Baset, Data Analyst, Shift Digital

Isfar Baset is a Data Analyst II at Shift Digital, a digital marketing firm, where she designs and scales data solutions supporting operational efficiency and client-facing analytics. She leads generative AI initiatives as Shift Digital expands its AI capabilities across digital marketing optimization. Her work spans analytics engineering, applied machine learning, and ETL pipeline development, with hands-on experience building end-to-end data pipelines, automating workflows, and delivering actionable insights in fast-paced, cross-functional environments. Her contributions include data migration and transformation projects in Databricks and the development of interactive dashboards that enabled faster decision-making for key stakeholders.

Faculty Speakers

Dr. Feifang Hu | Chair, Department of Statistics- George Washington University

Talk: AI Statisticians in Clinical Trials

Dr. Feifang Hu is currently the chair of the Department of Statistics at the George Washington University. He earned his PhD in statistics at the University of British Columbia in Vancouver. His research focuses on statistical issues in personalized medicine, bioinformatics, biostatistics, and financial econometrics. Hu has been awarded the Career Award from the National Science Foundation and served as a fellow at the Institute of Mathematical Statistics and American Statistical Association.

Hu is the author of a groundbreaking textbook “Theory of Response-Adaptive Randomization”, and multiple influential FDA white papers.  He served as associate editor for the Journal of the American Statistical Association (2011-2020), The Annals of Statistics (2007-2012), and Statistics and Its Interface (2007-2016). In 2018, Hu received the CCAS Dean’s Research Chair Award from George Washington University for his outstanding research in the design of clinical trials.

Dr. Qiwei Britt He | Provost’s Distinguished Associate Professor in the Data Science and Analytics- Georgetown University

Talk: Reimagining Future Educational Assessments Through Multimodal Data and AI Integration

Dr. Qiwei (Britt) He is a Provost’s Distinguished Associate Professor in the Data Science and Analytics Program and the Founder and Director of the AI Measurement and Data Science Lab at the Georgetown University Graduate School. She is also affiliated with the Massive Data Institute, the Department of Psychology, and the Department of Mathematics and Statistics at Georgetown. Currently, Dr. He is also appointed as Hughes Hall Visiting Fellow at University of Cambridge (2025-2026).

Her work centers on harnessing multimodal data—ranging from log‑file process traces of human–machine interactions to eye‑tracking signals, virtual‑reality behaviors, and rich textual responses—to illuminate the cognitive and behavioral processes underlying human performance. As a prominent expert in psychometrics and data science, Dr. He designs and analyzes large‑scale assessments for test development, digital measurement, and next‑generation psychometric modeling. She transforms complex behavioral and linguistic data into evidence‑informed insights that deepen our understanding of cognition, learning, and decision‑making. Her overarching research goal is to build innovative, digitally based assessment systems and analytic frameworks that more accurately capture latent traits at both individual and population levels. 

Dr. Michael Baron | Professor of Statistics- American University

Talk: Multiple Testing and Minimax Error Spending

Dr. Michael Baron is Professor of Statistics at American University, where he came after 18 years at the University of Texas at Dallas. He conducts research in the areas of sequential analysis, change-point detection, and multiple comparisons, applying obtained results in epidemiology, clinical trials, cybersecurity, energy finance, and semiconductor manufacturing. The last application brought M. Baron to IBM T. J. Watson Research Center, where he was a one-year Academic Visitor. M. Baron has published
two books; he is a Fellow of the American Statistical Association, an Elected Member of the International Statistical Institute, and a recipient of the Texas Regents Outstanding Teaching Award and the Abraham Wald prize for the best paper in sequential analysis.

Dr. Takumi Saegusa | Associate Professor- Statistics- University of Maryland

Talk: Data Integration: From Classical Sampling to Big Data

Dr. Takumi Saegusa is Associate Professor of Statistics at the Department of Mathematics, University of Maryland, College Park. His research focuses on the intersection of empirical process theory, complex sampling, and semi-parametric models. His work develops rigorous statistical methods motivated by practical problems in modern data analysis.

Dr. Wanli Qiao | Associate Professor- Statistics- George Mason University

Talk: From Modes to Ridges: Consistency of Mean Shift Algorithms

Dr. Wanli Qiao is an Associate Professor in the Department of Statistics at George Mason University. His research focuses on nonparametric statistics, geometric data analysis, machine learning, and extreme value theory, with particular interest in geometric structures arising from point cloud data. His collaborative work includes studying the geometric and topological properties of protein energy landscapes.

Student Speakers

Farshid Abadizaman | Ph.D. candidate in Applied Mathematics- Georgetown University

Talk: Efficient Bayesian Variable Selection under Predictor Dependence Regimes

Farshid Abadizaman is a Ph.D. candidate in Applied Mathematics, specializing in Bayesian learning for high-dimensional biological data. His research develops scalable and interpretable statistical models to uncover latent structures in -omics datasets, using stochastic search variable selection, sparse graphical modeling techniques, mixture models, and Markov chain Monte Carlo methods. His work supports applications in biomarker discovery, therapeutic target identification, and precision medicine.

Zixiang Xu | Ph.D. candidate in Statistics- George Mason University

Talk: Data Shift Problems Viewed from the Perspective of Selection Bias

Zixiang Xu is a Ph.D. candidate in Statistical Science at George Mason University, specializing in selection bias, data shifts, and statistical modeling for observational and clinical data. His research develops semiparametric and shape-constrained methods with applications ranging from astronomical observations to medical and real-world evidence analysis. Zixiang’s work has been recognized with awards including the Washington Statistical Society Outstanding Graduate Student Award.

Zeynep “Zedo” Yilmaz | UG in Data Science- American University

Talk: Predicting and Preventing Sports Injuries: A Data-Driven Classification Approach

Zeynep “Zedo” Yilmaz is an undergraduate student majoring in Data Science at American University. Her interests lie in sports analytics, with a particular focus on injury prevention and performance optimization in athletes. As an NCAA Division I volleyball player competing in the Patriot League, she brings firsthand experience to her analytical work. Zeynep has explored how athlete data can inform customized training programs to enhance off-season performance and reduce injury risk. Her work combines statistical analysis with practical applications in athletic training. She is especially interested in bridging data science and sports medicine to improve athlete health and longevity.

Jilei Lin | Ph.D. candidate in Statistics- George Washington University

Talk: Censored Bent-line Quantile Regression with Application in Experimental Autoimmune Myasthenia Gravis Studies

Selected photos from StatConnect 2025: