Title: “Multiple Markov Boundaries: the Good, the Bad, and the Ugly”
PhD Sisi Ma
Assistant Professor of Medicine, Division of General Internal Medicine, University of Minnesota.
Abstract: The Markov boundary of a response variable T is the minimal set of variables that renders all other variables in the dataset statistically independent of T. While some distributions admit a unique Markov boundary, others contain multiple distinct Markov boundaries for the same response. In this talk, I will introduce the theory of multiple Markov boundaries and explore potential mechanisms underlying their emergence in data, with a particular emphasis on biomedical data. I will also discuss the implications of multiple Markov boundaries for predictive modeling, causal modeling, and model translation into real-world decision support tools.
Dr. Ma’s primary research interest is the application of statistical modeling, machine learning, and causal analysis methods in the field of biology and medicine. Specifically, her approaches include: (1) devising and implementing new causal discovery methods that are specifically tailored to the characteristics of biomedical data, (2) benchmarking novel and existing causal discovery and predictive modeling methods in order to evaluate their efficacy on biomedical data, (3) designing analytical experiments to discover critical contributing factors to pathologies and diseases from multimodality high dimensional high volume data to aid the development of diagnostic technologies and identification of potential treatment targets.
CaDis 