Estimation and Inference in Regime-Switching Dynamic Networks

• Activity Number: 434
• Type: Contributed
• Date/Time: Tuesday, August 11, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Jing Ma* and George Michailidis
• Companies: University of Michigan and University of Florida
• Keywords: dynamic networks ; Gaussian graphical models ; regime switching

Abstract

We propose the Regime Switching Dynamic Networks to study the interactions between multiple time series using the framework of Gaussian graphical models. The interaction parameters (partial correlations) are assumed to come from two different regimes, with the transitions between the regimes modeled as linear. It is shown that the method performs well in a variety of settings and provides sensible empirical results.