Betsy Ogburn (Johns Hopkins Bloomberg School of Public Health)
Calvin Lab Room 116
Title: Disentangling Confounding and Nonsense Associations Due to Dependence
Abstract: Nonsense associations can arise when an exposure and an outcome of interest exhibit similar patterns of dependence. Confounding is present when potential outcomes are not independent of treatment. This talk will describe how confusion about these two phenomena results in limitations in popular methods in three areas: causal inference with multiple treatments and unmeasured confounding; causal and statistical inference with social network data; and causal inference with spatial data. For each of these three areas I will demonstrate the limitations of existing methods and describe new methods that were inspired by careful consideration of dependence and confounding.
Bio: Betsy Ogburn is Associate Professor of Biostatistics at Johns Hopkins Bloomberg School of Public Health. She is also a member of the Institute for Data-Intensive Engineering and Science at Johns Hopkins University and affiliated faculty of the SNF Agora Institute at Johns Hopkins and the Center for Causal Inference at University of Pennsylvania. She develops methods for learning causal relationships from non-experimental data. A major focus of her work is causal and statistical inference for social network data and other dependent data settings. Betsy completed her Ph.D. in Biostatistics at Harvard University. She is a 2016 National Academy of Science Kavli Fellow and 2022 COPSS Leadership Academy inductee.