A1462
Title: Machine learning panel data regressions with heavy-tailed dependent data: Theory and application
Authors: Jonas Striaukas - UCLouvain & FRS-FNRS (Belgium) [presenting]
Andrii Babii - University of North Carolina (United States)
Eric Ghysels - University of North Carolina Kenan and University of North Carolina at Chapel Hill (United States)
Ryan Ball - University of Michigan (United States)
Abstract: Machine learning regressions are introduced for heavy-tailed dependent panel data potentially sampled at different frequencies. We focus on the sparse-group LASSO regularization. This type of regularization can take advantage of the mixed frequency time series panel data structures and we find that it empirically outperforms the unstructured machine learning methods. We obtain oracle inequalities for the pooled and fixed effects sparse-group LASSO panel data estimators recognizing that financial and economic data can have fat tails. To that end, we leverage a new Fuk-Nagaev concentration inequality for panel data consisting of heavy-tailed tau-mixing processes. We also establish results for valid post-model-selection inference for pooled panel data estimators using HAC-based estimator for the long-run variance.
