Ker-Chau Li, Ph.D., distinguished professor in the department of statistics and data science at UCLA, will give a talk in the Department of Mathematical Sciences Statistics Seminar on Friday, Oct. 9, 2026, from 11:30 a.m. to 12:30 p.m. in HOS 380. The title of his talk is “Liquid Association and Conditional Dependence.” Refreshments will be served at 11:15 a.m.

Abstract: Liquid association (LA) is a higher-order concept of association involving three variables, X, Y, and Z (Li 2002, PNAS, “Genome-wide coexpression dynamics: Theory and Application”). LA depicts how the covariation pattern between X and Y may evolve internally as the value of a third variable changes. LA is especially useful for shedding light on why the correlations for certain pairs of mechanistically/functionally associated variables are zero or weak. It was originally introduced for exploring gene expression datasets at a time when such datasets were dominantly analyzed by correlation-driven methods, including principal component analysis and hierarchical clustering. In this talk, I will give a detailed account of the inception of LA. Then, I will review further developments and will explain why LA is fundamentally different from other conditional dependence measures.