Scientific article

A diagnostic criterion for approximate factor structure

Published inJournal of econometrics, vol. 212, p. 503-521
Publication date2019

We build a simple diagnostic criterion for approximate factor structure in large cross-sectional equity datasets. Given a model for asset returns with observable factors, the criterion checks whether the error terms are weakly cross-sectionally correlated or share at least one unobservable common factor. It only requires computing the largest eigenvalue of the empirical cross-sectional covariance matrix of the residuals of a large unbalanced panel. A general version of this criterion allows us to determine the number of omitted common factors. The panel data model accommodates both time-invariant and time-varying factor structures. The theory applies to random coefficient panel models with interactive fixed effects under large cross-section and time-series dimensions. The empirical analysis runs on monthly and quarterly returns for about ten thousand US stocks from January 1968 to December 2011 for several time-invariant and time-varying specifications. For monthly returns, we can choose either among time-invariant specifications with at least four financial factors, or a scaled three-factor time-varying specification. For quarterly returns, we cannot select macroeconomic models without the market factor.

  • Large panel
  • Approximate factor model
  • Asset pricing
  • Model selection
  • Interactive fixed effects
  • JEL : C12
Citation (ISO format)
GAGLIARDINI, Patrick, OSSOLA, Elisa, SCAILLET, Olivier. A diagnostic criterion for approximate factor structure. In: Journal of econometrics, 2019, vol. 212, p. 503–521. doi: 10.13097/archive-ouverte/unige:86121
Main files (1)
Article (Published version)
Secondary files (3)
ISSN of the journal0304-4076

Technical informations

Creation07/29/2016 12:52:00 PM
First validation07/29/2016 12:52:00 PM
Update time03/15/2023 12:37:56 AM
Status update03/15/2023 12:37:55 AM
Last indexation09/21/2023 12:39:34 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack