Variational Inference of Dynamic Factor Models with Arbitrary Missing Data

TL;DR

This paper introduces a variational inference method for dynamic factor models that efficiently handles arbitrary missing data patterns, providing accurate parameter uncertainty estimation with significant computational savings.

Contribution

It presents a novel variational inference approach for dynamic factor models that accommodates arbitrary missing data and offers a faster alternative to MCMC without sacrificing accuracy.

Findings

Approximate posterior captures factor features well

Method achieves high-precision predictive distributions

Significant computational efficiency compared to MCMC

Abstract

Dynamic factor models are often estimated by point-estimation methods, disregarding parameter uncertainty. We propose a method accounting for parameter uncertainty by means of posterior approximation, using variational inference. Our approach allows for any arbitrary pattern of missing data, including different sample sizes and mixed frequencies. It also yields a straight-forward estimation algorithm absent of time-consuming simulation techniques. In empirical examples using both small and large models, we compare our method to full Bayesian estimation from MCMC-simulations. Generally, the approximation captures factor features and parameters well, with vast computational gains. The resulting predictive distributions are approximated to a very high precision, almost indistinguishable from MCMC both in and out of sample, in a tiny fraction of computational time.