Applied Probability and Statistics seminar • University of St. Thomas • April 1, 2022
Abstract: Patients with advanced chronic kidney disease commonly experience debilitating symptoms, but the toxins that cause these symptoms are unknown. Metabolomics, the large-scale study of small molecules in biological samples, holds promise for identifying these toxins. In this talk, I’ll discuss the statistical approach that my collaborators and I used to investigate the metabolic underpinnings of these symptoms using data from the Modification of Diet in Renal Disease (MDRD) study. In particular, I’ll highlight common analysis frameworks used in studies of high-throughput biological measurements and the multi-pronged sensitivity analysis that we conducted to evaluate the robustness of our results.