Robustness and the General Dynamic Factor Model With Infinite-Dimensional Space: Identification, Estimation, and Forecasting

33 Pages Posted: 15 Jan 2020 Last revised: 30 Sep 2020

See all articles by Carlos Trucíos

Carlos Trucíos

Sao Paulo School of Economics, FGV.

João Henrique Gonçalves Mazzeu

Universidad Carlos III de Madrid

Luiz Koodi Hotta

University of Campinas (UNICAMP) - Department of Statistics

Pedro L. Valls Pereira

Sao Paulo School of Economics - FGV and CEQEF- FGV

Marc Hallin

ECARES, Universite Libre de Bruxelles

Date Written: September 30, 2020

Abstract

General dynamic factor models have demonstrated their capacity to circumvent the curse of dimensionality in the analysis of high-dimensional time series and have been successfully considered in many economic and financial applications. Being second-order models, however, they are sensitive to the presence of outliers---an issue that has not been analyzed so far in the general case of dynamic factors with possibly infinite-dimensional factor spaces (Forni et al.~2000, 2015, 2017). In this paper, we consider this robustness issue and study the impact of additive outliers on the identification, estimation, and forecasting performance of general dynamic factor models. Based on our findings, we propose robust versions of identification, estimation and forecasting procedures. The finite-sample performance of our methods is evaluated via Monte Carlo experiments and successfully applied to a classical dataset of 115 US macroeconomic and financial time series.

Keywords: Dimension reduction, Forecast, Jumps, Large panels

Suggested Citation

Trucíos Maza, Carlos César and Mazzeu, João Henrique Gonçalves and Hotta, Luiz Koodi and Valls Pereira, Pedro L. and Hallin, Marc, Robustness and the General Dynamic Factor Model With Infinite-Dimensional Space: Identification, Estimation, and Forecasting (September 30, 2020). Available at SSRN: https://ssrn.com/abstract=3509166 or http://dx.doi.org/10.2139/ssrn.3509166

Carlos César Trucíos Maza (Contact Author)

Sao Paulo School of Economics, FGV. ( email )

Rua Itapeva 474 s.1202
São Paulo, São Paulo 01332-000
Brazil

HOME PAGE: http://ctrucios.wixsite.com/personal

João Henrique Gonçalves Mazzeu

Universidad Carlos III de Madrid

CL. de Madrid 126
Madrid, 28903
Spain

Luiz Koodi Hotta

University of Campinas (UNICAMP) - Department of Statistics ( email )

Campinas, São Paulo 13083-859
Brazil

Pedro L. Valls Pereira

Sao Paulo School of Economics - FGV and CEQEF- FGV ( email )

Rua Itapeva 474 room 1006
São Paulo, São Paulo 01332-000
Brazil
55+11+37993726 (Phone)
55+11+37993357 (Fax)

HOME PAGE: http://sites.google.com/site/pedrovallspereira

Marc Hallin

ECARES, Universite Libre de Bruxelles ( email )

Ave. Franklin D Roosevelt, 50 - C.P. 114
Brussels, B-1050
Belgium
+32 2 650 5886 (Phone)
+32 2 650 5899 (Fax)

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
13
Abstract Views
161
PlumX Metrics