%0 Generic
%A Korobilis, Dimitris
%I Taylor & Francis
%D 2019
%G English
%T High-Dimensional Macroeconomic Forecasting Using Message Passing Algorithms
%U http://bonn.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1La8MwDBajhTIY7M3e-LBr2jRJ3fg4kobBSBmsl-4SFNd9wJqOJuvvn5QH9DQoO_og_IGwHtYnCeDZRhzoVPcpyXG0RVZSW6jpXUk3RX82TymC4A_9eKyiTzkZqfFeF3-tX6ZHaq6eci2fGUrl_hFp-15vrbrz1SJf4tZ0lRr2yaN3d2SE244cuJR-tcNpEEyrZuA_BMj2NpfsOZTo9P9QzqATkoz4MMU5HJnsAjpxXSe_hDemb1ghT-6vpm6IGMnimroLWfBCTo05U55FSRoQMa9CWRjxTsE0n1--Fpvtqliu8yuQ0WgSvFoNxOS7mlCRUGTPAJO1ShqASQ0w2TnuNZwg8-ezouyzm92AQDlDet_o9XXqpY7xPSX9OXqubXwceMNb6B14y93BEvdwTOFIuZ3BVg_QKrY_5hFa6SbLnmq1_gKkM7KM
%X This article 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 toward 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 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. Supplementary materials for this article are available online.
%K Medicine
%K Biotechnology
%K FOS: Computer and information sciences
%K Molecular Biology
%K FOS: Earth and related environmental sciences
%K FOS: Mathematics
%K Information Systems not elsewhere classified
%K Environmental Sciences not elsewhere classified
%K Mathematical Sciences not elsewhere classified