A0573
Title: Factor-augmented sparse MIDAS regressions with an application to nowcasting
Authors: Jonas Striaukas - Copenhagen Business School (Denmark) [presenting]
Jad Beyhum - KU Leuven (Belgium)
Abstract: The purpose is to investigate factor-augmented sparse MIDAS (mixed data sampling) regressions for high-dimensional time series data, which may be observed at different frequencies. The novel approach integrates sparse and dense dimensionality reduction techniques. The convergence rate of the estimator is derived under misspecification due to the MIDAS approximation error, $\tau$-mixing dependence, and polynomial tails. The method's finite sample performance is assessed via Monte Carlo simulations. The methodology is applied to nowcasting U.S. GDP growth, and it is demonstrated that it outperforms both sparse regression and standard factor-augmented regression during the COVID-19 pandemic. These findings indicate that the growth during the pandemic was influenced by both idiosyncratic (sparse) and common (dense) shocks.
