4 papers
Conditional projection methods for large-scale Bayesian VARs
Niko Hauzenberger, Michael Pfarrhofer
We develop fast methods for conditional forecasting and structural scenario analysis with high-dimensional Bayesian vector autoregressions (VARs). Our general framework features a…
A Bayesian Gaussian Process Dynamic Factor Model
Tony Chernis, Niko Hauzenberger, Haroon Mumtaz +1
We propose a dynamic factor model (DFM) where the latent factors are linked to observed variables with unknown and potentially nonlinear functions. The key novelty and source of fl…
Machine Learning the Macroeconomic Effects of Financial Shocks
Niko Hauzenberger, Florian Huber, Karin Klieber +1
We propose a method to learn the nonlinear impulse responses to structural shocks using neural networks, and apply it to uncover the effects of US financial shocks. The results rev…
Nowcasting with Mixed Frequency Data Using Gaussian Processes
Niko Hauzenberger, Massimiliano Marcellino, Michael Pfarrhofer +1
We develop Bayesian machine learning methods for mixed data sampling (MIDAS) regressions. This involves handling frequency mismatches and specifying functional relationships betwee…