Regularized Estimation of High-dimensional Factor-Augmented Vector Autoregressive (FAVAR) Models

A factor-augmented vector autoregressive (FAVAR) model is defined by a VAR equation that captures lead-lag correlations amongst a set of observed variables $X$ and latent factors $F$, and a calibration equation that relates another set of observed variables $Y$ with $F$ and $X$. The latter equation is used to estimate the factors that are subsequently used in estimating the parameters of the VAR system. The FAVAR model has become popular in applied economic research, since it can summarize a large number of variables of interest as a few factors through the calibration equation and subsequently examine their influence on core variables of primary interest through the VAR equation. However, there is increasing need for examining lead-lag relationships between a large number of time series, while incorporating information from another high-dimensional set of variables. Hence, in this paper we investigate the FAVAR model under high-dimensional scaling. We introduce an appropriate identification constraint for the model parameters, which when incorporated into the formulated optimization problem yields estimates with good statistical properties. Further, we address a number of technical challenges introduced by the fact that estimates of the VAR system model parameters are based on estimated rather than directly observed quantities. The performance of the proposed estimators is evaluated on synthetic data. Further, the model is applied to commodity prices and reveals interesting and interpretable relationships between the prices and the factors extracted from a set of global macroeconomic indicators.

[1]  Mark W. Watson,et al.  Twenty Years of Time Series Econometrics in Ten Pictures , 2017 .

[2]  J. Bai,et al.  Selecting the regularization parameters in high-dimensional panel data models: Consistency and efficiency , 2018 .

[3]  Kshitij Khare,et al.  High-Dimensional Posterior Consistency in Bayesian Vector Autoregressive Models , 2018, Journal of the American Statistical Association.

[4]  Efrem Castelnuovo,et al.  Working Paper No . 12 / 14 Uncertainty Shocks and Unemployment Dynamics in U . S . Recessions , 2014 .

[5]  M. Rosenblatt.  Stationary sequences and random fields , 1985 .

[6]  Garvesh Raskutti,et al.  Learning High-Dimensional Generalized Linear Autoregressive Models , 2019, IEEE Transactions on Information Theory.

[7]  J. Stock,et al.  Forecasting Using Principal Components From a Large Number of Predictors , 2002 .

[8]  B. Hofmann,et al.  Understanding Global Liquidity , 2013, SSRN Electronic Journal.

[9]  William B. Nicholson,et al.  VARX-L: Structured Regularization for Large Vector Autoregressions with Exogenous Variables , 2015, 1508.07497.

[10]  Ali Shojaie,et al.  Network granger causality with inherent grouping structure , 2012, J. Mach. Learn. Res..

[11]  A. Seth,et al.  Granger Causality Analysis in Neuroscience and Neuroimaging , 2015, The Journal of Neuroscience.

[12]  T. W. Anderson,et al.  Statistical analysis of time series , 1972 .

[13]  J. Frankel.  The Effect of Monetary Policy on Real Commodity Prices , 2006 .

[14]  C. Sims.  MACROECONOMICS AND REALITY , 1977 .

[15]  K. Chanda.  Asymptotic properties of estimators for autoregressive models with errors in variables , 1996 .

[16]  H. Yau,et al.  Bulk universality for generalized Wigner matrices , 2010, 1001.3453.

[17]  Po-Ling Loh,et al.  High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity , 2011, NIPS.

[18]  J. Frankel.  Effects of Speculation and Interest Rates in a "Carry Trade" Model of Commodity Prices , 2013 .

[19]  T. W. Anderson.  An Introduction to Multivariate Statistical Analysis , 1959 .

[20]  Martin J. Wainwright,et al.  High-Dimensional Statistics , 2019 .

[21]  Martin J. Wainwright,et al.  Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions , 2011, ICML.

[22]  Sumanta Basu,et al.  Large Spectral Density Matrix Estimation by Thresholding , 2018, 1812.00532.

[23]  George Michailidis,et al.  Regularized Estimation and Testing for High-Dimensional Multi-Block Vector-Autoregressive Models , 2017, J. Mach. Learn. Res..

[24]  Robert B. Litterman.  Forecasting with Bayesian Vector Autoregressions-Five Years of Experience , 1984 .

[25]  G. Michailidis,et al.  Regularized estimation in sparse high-dimensional time series models , 2013, 1311.4175.

[26]  Anja Vogler,et al.  An Introduction to Multivariate Statistical Analysis , 2004 .

[27]  Helmut Ltkepohl,et al.  New Introduction to Multiple Time Series Analysis , 2007 .

[28]  Jean Boivin,et al.  Measuring the Effects of Monetary Policy: A Factor-Augmented Vector Autoregressive (FAVAR) Approach , 2003 .

[29]  A. Willsky,et al.  Latent variable graphical model selection via convex optimization , 2010 .

[30]  Rebecca Willett,et al.  Inference of High-dimensional Autoregressive Generalized Linear Models , 2016, ArXiv.

[31]  T. Cipra.  Statistical Analysis of Time Series , 2010 .

[32]  Martin J. Wainwright,et al.  A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers , 2009, NIPS.

[33]  Martin J. Wainwright,et al.  Estimation of (near) low-rank matrices with noise and high-dimensional scaling , 2009, ICML.

[34]  Ali Shojaie,et al.  Discovering graphical Granger causality using the truncating lasso penalty , 2010, Bioinform..

[35]  Emmanuel J. Candès,et al.  Matrix Completion With Noise , 2009, Proceedings of the IEEE.

[36]  Serena Ng,et al.  MEASUREMENT ERRORS IN DYNAMIC MODELS , 2013, Econometric Theory.

[37]  Joydeep Ghosh,et al.  Unified View of Matrix Completion under General Structural Constraints , 2015, NIPS.

[38]  Helmut Lütkepohl,et al.  Structural Vector Autoregressive Analysis in a Data Rich Environment: A Survey , 2014 .

[39]  Yong He,et al.  Large-Dimensional Factor Analysis Without Moment Constraints , 2019, Journal of Business & Economic Statistics.

[40]  Mark W. Watson,et al.  Dynamic Factor Models, Factor-Augmented Vector Autoregressions, and Structural Vector Autoregressions in Macroeconomics , 2016 .

[41]  Holger Sambale,et al.  Concentration inequalities for polynomials in α-sub-exponential random variables , 2019, Electronic Journal of Probability.

[42]  Kunpeng Li,et al.  Estimation and Inference of FAVAR Models , 2014 .

[43]  Martin J. Wainwright,et al.  Restricted strong convexity and weighted matrix completion: Optimal bounds with noise , 2010, J. Mach. Learn. Res..

[44]  D. Giannone,et al.  Large Bayesian vector auto regressions , 2010 .

[45]  Martin J. Wainwright,et al.  Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$ -Constrained Quadratic Programming (Lasso) , 2009, IEEE Transactions on Information Theory.

[46]  Arindam Banerjee,et al.  Estimating Structured Vector Autoregressive Models , 2016, ICML.