A Diagnostic Criterion For Approximate Factor Structure
Event details
Date | 12.04.2016 |
Hour | 12:15 › 13:15 |
Speaker | Patrick GAGLIARDINI (USI, University of Lugano) |
Location | |
Category | Conferences - Seminars |
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. We also explain how to compute p-values via sample conditioning and randomization. The panel data model accommodates both time-invariant and time-varying factor structures. The theory applies to generic random coefficient panel models under large crosssection and time-series dimensions. The empirical analysis runs on monthly returns for about ten thousand US stocks from January 1968 to December 2011 for several time-varying specifications. Among several multi-factor time-invariant models proposed in the literature, we cannot select a model with zero factors in the errors. On the opposite, we conclude for no omitted factor structure in the errors for several time-varying specifications.
Links
Practical information
- Informed public
- Free