A Quasi–Maximum Likelihood Approach for Large, Approximate Dynamic Factor Models

Catherine Doz; Domenico Giannone; Lucrezia Reichlin

doi:10.1162/rest_a_00225

The Review of Economics and Statistics Vol. 94 No. 4 2012

A Quasi–Maximum Likelihood Approach for Large, Approximate Dynamic Factor Models

Catherine Doz^1,2,3; Domenico Giannone^4,5,6; Lucrezia Reichlin^6,7

¹ Centre d'Économie de la Sorbonne · ² Université Paris 1 Panthéon-Sorbonne · ³ Paris School of Economics · ⁴ Université Libre de Bruxelles · ⁵ European Institute for Advanced Studies in Management · ⁶ Centre for Economic Policy Research · ⁷ London Business School

Abstract

Is maximum likelihood suitable for factor models in large cross-sections of time series? We answer this question from both an asymptotic and an empirical perspective. We show that estimates of the common factors based on maximum likelihood are consistent for the size of the cross-section (n) and the sample size (T), going to infinity along any path, and that maximum likelihood is viable for n large. The estimator is robust to misspecification of cross-sectional and time series correlation of the idiosyncratic components. In practice, the estimator can be easily implemented using the Kalman smoother and the EM algorithm as in traditional factor analysis.

DOI: 10.1162/rest_a_00225
Volume: 94
Issue: 4
Pages: 1014-1024
Language: en
Sources: crossref openalex

A Quasi–Maximum Likelihood Approach for Large, Approximate Dynamic Factor Models

Abstract

Cite