Micro Theory Work in Progress
Econometrics Seminar - Patrick Gagliardini (Lugano)
Title: Eigenvalue tests for the number of latent factorsin short panels
Alain-Philippe Fortin, Patrick Gagliardini, Olivier Scaillet
This paper studies new tests for the number of latent factors in a large cross-sectionalfactor model with small time dimension. These tests are based on the eigenvalues ofvariance-covariance matrices. We establish the asymptotic distributional results usingexpansion theorems based on perturbation theory for symmetric matrices. Our frame-work accommodates semi-strong factors in the systematic components. We propose anovel statistical test for weak factors against strong or semi-strong factors. We providean empirical application to US equity data. Evidence for a dierent number of latentfactors according to market downturns and market upturns, is statistically ambiguous.In particular, our results contradicts the common wisdom of a single factor model inbear markets