EconBase
← All papers

Machine Learning Time Series Regressions with an Application to Nowcasting

Andrii Babii, Eric Ghysels, Jonas Striaukas

arXiv 28 May 2020 · Econometrics · publishedJournal of Business and Economic Statistics (2021) · 32 citations (OpenAlex)

arXiv:2005.14057 · PDF · DOI · OpenAlex · Extracted main text

Abstract

This paper introduces structured machine learning regressions for high-dimensional time series data potentially sampled at different frequencies. The sparse-group LASSO estimator can take advantage of such time series data structures and outperforms the unstructured LASSO. We establish oracle inequalities for the sparse-group LASSO estimator within a framework that allows for the mixing processes and recognizes that the financial and the macroeconomic data may have heavier than exponential tails. An empirical application to nowcasting US GDP growth indicates that the estimator performs favorably compared to other alternatives and that text data can be a useful addition to more traditional numerical data.

Citation extraction

60
references
91
in-text mentions
60
distinct cited
2
self-citations
10,346
main-text words

appendix boundary found by appendix_titled_section at “Dictionaries \label{appendix:dictionaries}” · 64% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Bybee, Kelly, Manela, and Xiu (2020) The structure of economic news0.8434375%
2Babii, Ghysels, and Striaukas (2020) Inference for high-dimensional regressions with heteroskedasticity and autocorrelation self0.8307457%
3Bok, Caratelli, Giannone, Sbordone, and Tambalotti (2018) Macroeconomic nowcasting and forecasting with big data0.81142100%
4Dedecker and Prieur (2004) Coupling for $$-dependent sequences and applications0.81142100%
5Dedecker and Prieur (2005) New dependence coefficients. Examples and applications to statistics0.7373367%
6Quaedvlieg (2019) Multi-horizon forecast comparison0.64441100%
7Andreou, Ghysels, and Kourtellos (2013) Should macroeconomic forecasters use daily financial data and how?0.64422100%
8Belloni, Chernozhukov, Chetverikov, Hansen, and Kato (2020) High-dimensional econometrics and generalized GMM0.64422100%
9Carrasco and Chen (2002) Mixing and moment properties of various GARCH and stochastic volatility models0.64422100%
10Chernozhukov, Härdle, Huang, and Wang (2020) Lasso-driven inference in time and space0.64422100%

Showing the top 10 of 60 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Nowcasting and aggregation: Why small Euro area countries matter1.000133
2High-dimensional censored MIDAS logistic regression for corporate survival forecasting1.000114
3High-Dimensional Granger Causality Tests with an Application to VIX and News1.00084
4Machine Learning Panel Data Regressions with Heavy-tailed Dependent Data: Theory and Application0.888104
5Hierarchical Regularizers for Mixed-Frequency Vector Autoregressions0.81142
6Factor-Augmented Machine Learning Panel Regressions0.81142
7Macroeconomic forecasting with LSTM and mixed frequency time series data0.73732
8Hierarchical Regularizers for Reverse Unrestricted Mixed Data Sampling Regressions0.73732
9Sparse Tree-Based Aggregation for Time Series Regressions0.73732
10Econometrics of Machine Learning Methods in Economic Forecasting0.69361