A Spectral EM Algorithm for Dynamic Factor Models
62 Pages Posted: 1 Oct 2016
Date Written: September 30, 2016
We make two complementary contributions to efficiently estimate dynamic factor models: a frequency domain EM algorithm and a swift iterated indirect inference procedure for ARMA models with no asymptotic efficiency loss for any finite number of iterations. Although our procedures can estimate such models with many series without good initial values, near the optimum we recommend switching to a gradient method that analytically computes spectral scores using the EM principle. We successfully employ our methods to construct an index that captures the common movements of US sectoral employment growth rates, which we compare to the indices obtained by semi-parametric methods.
Keywords: indirect inference, Kalman filter, sectoral employment, spectral maximum likelihood, Wiener-Kolmogorov filter
JEL Classification: C32, C38, C51
Suggested Citation: Suggested Citation