TADA-BSSR Webinar
Avoiding the Pitfalls of Selection Bias
Date: January 21, 2021
Time: 10:00 – 11:00 AM Pacific / 1:00 – 2:00 PM Eastern Time
Lecturer: Carl T. Bergstrom, PhD, University of Washington
Overview: Selection bias occurs when the method by which a statistical sample is obtained prevents the sample from accurately representing the population about which one wishes to draw inferences. As straightforward as the issue may seem, selection bias is among the most pernicious perils of statistical inference. In this lecture, Dr. Carl T. Bergstrom will discuss some of the many ways that selection bias and related phenomena, from right censoring to the “Will Rogers effect,” can arise in medical research and beyond. He will draw from a range of examples, including recent studies on COVID-19. The session will feature interactive audience questions and answers, using the chat function of the live Zoom session.
_________
The Training in Advanced Data Analytics for Behavioral and Social Sciences (TADA-BSSR) Webinar Series is a virtual lecture series that covers advanced data analytics and data science underlying modern behavioral and social sciences research, with presentations from experts showing the basics of data management, representation, computation, statistical inference, data modeling, causal inference, and various other topics relevant to “big data” and teaching for behavioral and social sciences researchers. The TADA-BSSR program supports Behavioral and Social Sciences Research (BSSR) predoctoral training programs that focus on innovative computational and/or data science analytic approaches and their incorporation into training for the future BSSR health research workforce. The vision of the TADA-BSSR program is to support the development of a cohort of specialized predoctoral candidates who will possess advanced competencies in data science analytics to apply to an increasingly complex landscape of behavioral and social health-related big data. This series highlights research projects and topics in scope of the Computational Social Science Training Program at BIDS, as well as related programs at other national universities that are funded by the National Institutes of Health (NIH) Office of Behavioral and Social Sciences Research (OBSSR). The program at BIDS is aligned with the Eunice Kennedy Shriver National Institute of Child Health and Human Development.
Speaker(s)
Carl T. Bergstrom, PhD
Carl Bergstrom is a professor in the Department of Biology at the University of Washington. Dr. Bergstrom’s research uses mathematical, computational, and statistical models to understand how information flows through biological and social systems. His recent projects include contributions to the game theory of communication and deception, the use of information theory to the study of evolution by natural selection, game-theoretic models and empirical work on the sociology of science, and the development of mathematical techniques for mapping and comprehending large network datasets. In the applied domain, Dr. Bergstrom’s work illustrates the value of evolutionary biology for solving practical problems in medicine and beyond. These problems include studying drug resistance, handling the economic externalities associated with anthropogenic evolution, and controlling novel emerging pathogens, such as the SARS virus, Ebola virus, and H5N1 avian influenza virus.
Dr. Bergstrom is the coauthor of Evolution, a college textbook published by W. W. Norton and Co. He teaches undergraduate courses on evolutionary biology and evolutionary game theory, as well as the importance of evolutionary biology to the fields of medicine and public health. Dr. Bergstrom received his Ph.D. in theoretical population genetics from Stanford University in 1998; in 2001, after a 2-year postdoctoral fellowship at Emory University, where he studied the ecology and evolution of infectious diseases, he joined the faculty at the University of Washington.