Universität zu Köln

Umbach, Simon Lineu (2020). Forecasting with supervised factor models. Empir. Econ., 58 (1). S. 169 - 191. HEIDELBERG: PHYSICA-VERLAG GMBH & CO. ISSN 1435-8921

Full text not available from this repository.

Abstract

A conventional approach to forecast in a data-rich environment is to estimate factor-augmented predictive regressions with factors constructed by principal component analysis. This study analyzes under which circumstances gains in forecast accuracy can be achieved by incorporating some form of supervision in the factor estimation process. Specifically, principal covariate regression (PCovR) is considered. For the problem of choosing a value for the supervision parameter in PCovR, an information criterion is proposed. The information criterion is shown to be an appropriate means to find a good balance between predictor space compression and target orientation of the estimated factors. A simulation study and an empirical application on a macroeconomic dataset show that supervised factors can improve the forecasting accuracy of factor models.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Umbach, Simon Lineu UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-351542
DOI:	10.1007/s00181-019-01745-x
Journal or Publication Title:	Empir. Econ.
Volume:	58
Number:	1
Page Range:	S. 169 - 191
Date:	2020
Publisher:	PHYSICA-VERLAG GMBH & CO
Place of Publication:	HEIDELBERG
ISSN:	1435-8921
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language REGRESSION; SELECTION Multiple languages Economics; Social Sciences, Mathematical Methods Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/35154