High-Dimensional Macroeconomic Forecasting Using Message Passing Algorithms

This paper proposes two distinct contributions to econometric analysis of large information sets and structural instabilities. First, it treats a regression model with time-varying coefficients, stochastic volatility and exogenous predictors, as an equivalent high-dimensional static regression problem with thousands of covariates. Inference in this specification proceeds using Bayesian hierarchical priors that shrink the high-dimensional vector of coefficients either towards zero or time-invariance. Second, it introduces the frameworks of factor graphs and message passing as a means of designing efficient Bayesian estimation algorithms. In particular, a Generalized Approximate Message Passing (GAMP) algorithm is derived that has low algorithmic complexity and is trivially parallelizable. The result is a comprehensive methodology that can be used to estimate time-varying parameter regressions with arbitrarily large number of exogenous predictors. In a forecasting exercise for U.S. price inflation this methodology is shown to work very well.

[1]  Joshua C. C. Chan,et al.  Time Varying Dimension Models , 2011 .

[2]  R. Kohn,et al.  Efficient Bayesian Inference for Multiple Change-Point and Mixture Innovation Models , 2005 .

[3]  Judea Pearl,et al.  Reverend Bayes on Inference Engines: A Distributed Hierarchical Approach , 1982, AAAI.

[4]  Sundeep Rangan,et al.  Generalized approximate message passing for estimation with random linear mixing , 2010, 2011 IEEE International Symposium on Information Theory Proceedings.

[5]  M. West,et al.  Bayesian Analysis of Latent Threshold Dynamic Models , 2013 .

[6]  Bhaskar D. Rao,et al.  A GAMP-Based Low Complexity Sparse Bayesian Learning Algorithm , 2017, IEEE Transactions on Signal Processing.

[7]  Jonathan H. Wright,et al.  Forecasting Inflation , 2011 .

[8]  David S. Matteson,et al.  Dynamic shrinkage processes , 2017, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[9]  Brendan J. Frey,et al.  Factor graphs and the sum-product algorithm , 2001, IEEE Trans. Inf. Theory.

[10]  S. Frühwirth-Schnatter,et al.  Stochastic model specification search for Gaussian and partial non-Gaussian state space models , 2010 .

[11]  Jun Fang,et al.  Computationally efficient sparse Bayesian learning via generalized approximate message passing , 2015, 2016 IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB).

[12]  J. Stock,et al.  Why Has U.S. Inflation Become Harder to Forecast? , 2006 .

[13]  Dimitris Korobilis,et al.  Hierarchical Shrinkage Priors for Dynamic Regressions with Many Predictors , 2011 .

[14]  J. Griffin,et al.  Time-Varying Sparsity in Dynamic Regression Models , 2013 .

[15]  David Barber,et al.  Bayesian reasoning and machine learning , 2012 .

[16]  M. P. Wand,et al.  Fast Approximate Inference for Arbitrarily Large Semiparametric Regression Models via Message Passing , 2016, 1602.07412.

[17]  T. Sargent,et al.  Drifts and Volatilities: Monetary Policies and Outcomes in the Post WWII U.S. , 2003 .

[18]  E. George,et al.  Journal of the American Statistical Association is currently published by American Statistical Association. , 2007 .

[19]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[20]  Aki Vehtari,et al.  Expectation Propagation as a Way of Life: A Framework for Bayesian Inference on Partitioned Data , 2014, J. Mach. Learn. Res..

[21]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[22]  Edward C. Prescott,et al.  Estimation in the Presence of Stochastic Parameter Variation , 1976 .

[23]  Volkan Cevher,et al.  Fixed Points of Generalized Approximate Message Passing With Arbitrary Matrices , 2016, IEEE Transactions on Information Theory.

[24]  Davide Pettenuzzo,et al.  Forecasting Macroeconomic Variables Under Model Instability , 2016 .

[25]  Dimitris Korobilis,et al.  The Contribution of Structural Break Models to Forecasting Macroeconomic Series , 2013 .

[26]  Francesco Ravazzolo,et al.  Real-Time Inflation Forecasting in a Changing World , 2013 .

[27]  Mu-Chun Wang,et al.  Choosing Prior Hyperparameters: With Applications to Time-Varying Parameter Models , 2018, Journal of Business & Economic Statistics.

[28]  Hilbert J. Kappen,et al.  Sufficient Conditions for Convergence of the Sum–Product Algorithm , 2005, IEEE Transactions on Information Theory.

[29]  V. Rocková,et al.  Dynamic Variable Selection with Spike-and-Slab Process Priors , 2017, Bayesian Analysis.

[30]  G. Koop,et al.  Bayesian Multivariate Time Series Methods for Empirical Macroeconomics , 2009 .