Measuring Systemic Risk with Network Connectivity: Extended Abstract

摘要: Measuring connectedness among financial institutions is an important aspect of monitoring systemwide risk development and identifying systemically risky institutions. In this work, we present a novel statistical method for measuring connectivity firms using publicly available time series firm-level characteristics. The proposed relies on Lasso penalized estimation high-dimensional vector autoregressive models (VAR) provides principled framework estimating network topology linkages firms. We apply our to analyze stock returns leading in the U.S. before, during after crisis 2007-2009, show that centrality measures estimated networks can be used identify systemic events