STATISTICS COLLOQUIUM
Yong Chen
Associate Professor
Department of Biostatistics, Epidemiology and Informatics
Perelman School of Medicine, University of Pennsylvania
Non-standard problems in statistical inference:
Bartlett identity, boundary, identifiability issues
Abstract
In this talk, I will cover a few ideas in tackling non-standard problems in statistical inference, including Bartlett identity, boundary and identifiability issues. I will show that these considerations are critical in model robustness, statistical power, and validity. I will also present implications of these ideas in addressing some challenges in biomedical research including analysis of DNA methylation data and drug/vaccine safety data.
Bio: Dr. Yong Chen is an Associate Professor of Biostatistics at the Department of Biostatistics, Epidemiology and Informatics (DBEI), the Perelman School of Medicine, University of Pennsylvania (Penn). He is the PI of the PennCIL lab, which is aiming to tackle key challenges in the modern data rich era, including heterogeneity, complexity, suboptimal quality, reproducibility, privacy, and high-dimensionality of biomedical data. He has published over 100 papers. His research has been continuously funded by NIH, PCORI and AHRQ.
Dr. Chen holds joint appointments at the Institute of Biomedical Informatics, the Center for Evidence-based Practice, and the Applied Mathematics & Computational Science Program at the University of Pennsylvania. He obtained his Ph.D. in Biostatistics from the Johns Hopkins University. He has received numerous award including the Elected Fellow of American Statistical Association in 2020.
For more information, contact: Tracy Burke at tracy.burke@uconn.edu