Medical School Office Building (MSOB)
|DATE:||February 15, 2018|
|TIME:||1:30 - 2:50 pm|
|TITLE:||Enabling likelihood-based inference for complex and dependent biomedical data|
Postdoctoral Scholar, Department of Biomathematics, University of California, Los Angeles
The likelihood function is central to many principled approaches to statistical inference, but poses mathematical and computational challenges in modern data analysis. Motivated by emergent cell lineage tracking experiments to study blood cell production, we present recent methods that newly enable likelihood-based inference for partially observed data arising from count-valued stochastic processes that evolve continuously through time. These advances make feasible principled procedures such as maximum likelihood estimation, posterior inference, and expectation-maximization (EM) algorithms in previously intractable data settings. We discuss limitations and alternatives when data are very large or generated from a hidden process, and address some of the remaining challenges using optimization. We highlight majorization-minimization (MM) algorithms, a generalization of EM, showcasing their advantages over existing state-of-the-art on classical inference problems with application to cell signaling and EEG data.