Econometrica: Sep 2009, Volume 77, Issue 5

Testing Hypotheses About the Number of Factors in Large Factor Models

https://doi.org/10.3982/ECTA6964
p. 1447-1479

Alexei Onatski

In this paper we study high‐dimensional time series that have the generalized dynamic factor structure. We develop a test of the null of factors against the alternative that the number of factors is larger than but no larger than >. Our test statistic equals max(γ−γ)(γ−γ), where γ is the th largest eigenvalue of the smoothed periodogram estimate of the spectral density matrix of data at a prespecified frequency. We describe the asymptotic distribution of the statistic, as the dimensionality and the number of observations rise, as a function of the Tracy–Widom distribution and tabulate the critical values of the test. As an application, we test different hypotheses about the number of dynamic factors in macroeconomic time series and about the number of dynamic factors driving excess stock returns.

Log In To View Full Content

Supplemental Material

Supplement to "Testing hypotheses about the number of factors in large factor models"

A zip file that includes data and programs.

Read More View ZIP


Supplement to "Testing hypotheses about the number of factors in large factor models"

A pdf file containing detailed proofs.

Read More View PDF


Back