Nowcasting with mixed frequency data using Gaussian processes

arXiv:2402.10574v1 Announce Type: cross
Abstract: We propose and discuss Bayesian machine learning methods for mixed data sampling (MIDAS) regressions. This involves handling frequency mismatches with restricted and unrestricted MIDAS variants and specifying functional relationships between many predictors and the dependent variable. We use Gaussian processes (GP) and Bayesian additive regression trees (BART) as flexible extensions to linear penalized estimation. In a nowcasting and forecasting exercise we focus on quarterly US output growth and inflation in the GDP deflator. The new …

abstract arxiv bart bayesian data discuss econ.em functional gaussian processes machine machine learning mixed nowcasting processes regression relationships sampling stat.ml trees type variants