Deep Neural Network Estimation in Panel Data Models

68 Pages Posted: 29 Jan 2024

See all articles by Ilias Chronopoulos

Ilias Chronopoulos

affiliation not provided to SSRN

Katerina Chrysikou

affiliation not provided to SSRN

George Kapetanios

King's College, London

James Mitchell

Federal Reserve Bank of Cleveland

Aristeidis Raftapostolos

King’s College London - King's Business School

Date Written: July 5, 2023

Abstract

In this paper we study neural networks and their approximating power in panel data models. We provide asymptotic guarantees on deep feed-forward neural network estimation of the conditional mean, building on the work of Farrell et al. (2021), and explore latent patterns in the cross-section. We use the proposed estimators to forecast the progression of new COVID-19 cases across the G7 countries during the pandemic. We find significant forecasting gains over both linear panel and nonlinear time-series models. Containment or lockdown policies, as instigated at the national level by governments, are found to have out-of-sample predictive power for new COVID-19 cases. We illustrate how the use of partial derivatives can help open the “black box” of neural networks and facilitate semi-structural analysis: school and workplace closures are found to have been effective policies at restricting the progression of the pandemic across the G7 countries. But our methods illustrate significant heterogeneity and time variation in the effectiveness of specific containment policies.

Note:
Funding Information: None.

Conflict of Interests: None.

Keywords: Machine Learning, Neural Networks, Panel Data, Nonlinearity, Forecasting, COVID-19, Policy Interventions

JEL Classification: C33, C45

Suggested Citation

Chronopoulos, Ilias and Chrysikou, Katerina and Kapetanios, George and Mitchell, James and Raftapostolos, Aristeidis, Deep Neural Network Estimation in Panel Data Models (July 5, 2023). FRB of Cleveland Working Paper No. 23-15, https://doi.org/10.26509/frbc-wp-202315, Available at SSRN: https://ssrn.com/abstract=4501438 or http://dx.doi.org/10.2139/ssrn.4501438

Ilias Chronopoulos

affiliation not provided to SSRN

Katerina Chrysikou

affiliation not provided to SSRN

George Kapetanios

King's College, London ( email )

30 Aldwych
London, WC2B 4BG
United Kingdom
+44 20 78484951 (Phone)

James Mitchell (Contact Author)

Federal Reserve Bank of Cleveland ( email )

East 6th & Superior
Cleveland, OH 44101-1387
United States

HOME PAGE: http://https://www.clevelandfed.org/en/our-research/economists/james-mitchell.aspx

Aristeidis Raftapostolos

King’s College London - King's Business School ( email )

Strand Campus
London, WC2R 2LS
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
64
Abstract Views
301
Rank
705,067
PlumX Metrics