Title: Estimating time-varying networks with a state-space model
Authors: Shaowen Liu - University of Padova (Italy)
Massimiliano Caporin - University of Padova (Italy)
Sandra Paterlini - University of Trento (Italy) [presenting]
Abstract: A state-space model (SSM) is proposed to estimate dynamic spatial relationships from time-series data. At each time step, the weight matrix, capturing the latent state, is updated by a spatial autoregressive model. Specifically, we consider two types of SSM: the first one calibrates the spatial model to a multivariate regression. In contrast, the second one updates the spatial matrix by leveraging the maximum likelihood (ML) estimation. Simulation results show that the first model performs robustly for all cases, while the performance of the second model is more sensitive to the state dimension. Then, we estimate the time-varying weight matrices with weekly credit default swap (CDS) data for 16 banks and show that the methods identify communities which are coherent with the country-driven partitions.