A Randomized Missing Data Approach to Robust Filtering with Applications to Economics and Finance

Dobrislav Dobrev     Derek Hansen     Pawel J. Szerszen∗ 

 

 

Abstract:  We put forward a simple new approach to robust filtering of state-space models, motivated by the idea that the inclusion of only a small fraction of available highly precise measurements can still extract most of the attainable efficiency gains for filtering latent states, estimating model parameters, and producing out-of-sample forecasts. The new class of particle filters we develop aims to achieve a degree of robustness to outliers and model misspecification by purposely randomizing the subset of utilized highly precise but possibly misspecified or outlier contaminated data measurements, while treating the rest as if missing. The arising robustness-efficiency trade-off is controlled by varying the fraction of randomly utilized measurements or the incurred relative efficiency loss from such randomized utilization of the available measurements. As an empirical illustration, we consider popular state space models for inflation and equity returns with stochastic volatility and document favorable performance of our robust particle filter and density forecasts on both simulated and real data. More generally, our randomization approach makes it easy to robustly incorporate highly informative but possibly contaminated modern “big data” streams for improved state-space filtering and forecasting.

∗All authors are at the Board of Governors of the Federal Reserve System, 20th St. and Constitution Ave. NW, Washington, DC 20551. Emails: This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it. and This email address is being protected from spambots. You need JavaScript enabled to view it.. We are grateful to Nicholas Polson, Tatevik Sekhposyan and Jonathan Wright for very helpful discussions and comments. We also thank conference participants at the 2nd Workshop on Financial Econometrics and Empirical Modeling of Financial Markets, Kiel Institute for the World Economy, May 3-4, 2018 and the 2018 NBER-NSF Seminar on Bayesian Inference in Econometrics and Statistics (SBIES), Stanford University, May 25-26, 2018, as well as seminar participants at the Federal Reserve Board of Governors. This article represents the views of the authors, and should not be interpreted as reflecting the views of the Board of Governors of the Federal Reserve System or other members of its staff.