This is a past event.

Speaker: Professor Inyoung Kim (Department of Statistics, Virginia Tech).

ABSTRACT: In this talk, I will introduce a joint estimation method for building a multilevel Gaussian graphical model. The Gaussian graphical model has been a popular tool for investigating the conditional dependency structure between random variables by estimating sparse precision matrices. The estimated precision matrices can be mapped into networks for visualization. However, the ability to investigate the conditional dependency structure when a multi-level structure exists among the variables is still limited. Some variables are considered as higher-level variables, while others are nested in these higher-level variables—the latter is called lower-level variables. Higher-level variables are not isolated; instead, they work together to accomplish certain tasks. In this talk, I will introduce a joint estimation method to simultaneously explore conditional dependency structures among higher-level variables and lower-level variables.