Dynamic Score-Driven Independent Component Analysis

The pseudo-likelihood score of the model innovation rotation angle drives a novel dynamic independent component analysis model. Simulated results show the model’s pseudo maximum likelihood estimator is consistent and asymptotically normally distributed. The model matches financial stress narratives during the global financial crisis, European sovereign debt crisis, and Brexit speculations when applied to a bivariate exchange rate series. These findings corroborate a recent geopolitical risk-portfolio kurtosis model.

Image courtesy of interviewee. December 19, 2023

Copyright © Faculti Media Limited 2013 - 2024. All rights reserved.