Large Vector Auto Regressions

One popular approach for nonstructural economic and financial forecasting is to include a large number of economic and financial variables, which has been shown to lead to significant improvements for forecasting, for example, by the dynamic factor models. A challenging issue is to determine which variables and (their) lags are relevant, especially when there is a mixture of serial correlation (temporal dynamics), high dimensional (spatial) dependence structure and moderate sample size (relative to dimensionality and lags). To this end, an integrated solution that addresses these three challenges simultaneously is appealing. We study the large vector auto regressions here with three types of estimates. We treat each variable's own lags different from other variables' lags, distinguish various lags over time, and is able to select the variables and lags simultaneously. We first show the consequences of using Lasso type estimate directly for time series without considering the temporal dependence. In contrast, our proposed method can still produce an estimate as efficient as an oracle under such scenarios. The tuning parameters are chosen via a data driven "rolling scheme" method to optimize the forecasting performance. A macroeconomic and financial forecasting problem is considered to illustrate its superiority over existing estimators.

[1]  Thomas J. Sargent,et al.  Business cycle modeling without pretending to have too much a priori economic theory , 1976 .

[2]  Robert B. Litterman,et al.  Forecasting and Conditional Projection Using Realistic Prior Distributions , 1983 .

[3]  A. Siegel,et al.  Parsimonious modeling of yield curves , 1987 .

[4]  P. Bickel.  Efficient and Adaptive Estimation for Semiparametric Models , 1993 .

[5]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[6]  K. Do,et al.  Efficient and Adaptive Estimation for Semiparametric Models. , 1994 .

[7]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[8]  Lawrence J. Christiano,et al.  Monetary Policy Shocks: What Have We Learned and to What End? , 1998 .

[9]  M. Hallin,et al.  The Generalized Dynamic-Factor Model: Identification and Estimation , 2000, Review of Economics and Statistics.

[10]  Jianqing Fan,et al.  Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties , 2001 .

[11]  Alan C. Evans,et al.  A General Statistical Analysis for fMRI Data , 2000, NeuroImage.

[12]  F. Diebold,et al.  Forecasting the Term Structure of Government Bond Yields , 2002 .

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

[14]  J. Stock,et al.  Macroeconomic Forecasting Using Diffusion Indexes , 2002 .

[15]  Marco Lippi,et al.  The Generalized Dynamic Factor Model , 2002 .

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

[17]  Matthias R. Fengler,et al.  Implied Volatility String Dynamics , 2003 .

[18]  Svante Janson,et al.  Large deviations for sums of partly dependent random variables , 2004, Random Struct. Algorithms.

[19]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.

[20]  Mark W. Watson,et al.  AN EMPIRICAL COMPARISON OF METHODS FOR FORECASTING USING MANY PREDICTORS , 2005 .

[21]  C. De Mol,et al.  Forecasting Using a Large Number of Predictors: Is Bayesian Regression a Valid Alternative to Principal Components? , 2006, SSRN Electronic Journal.

[22]  Wolfgang Härdle,et al.  A semiparametric factor model for implied volatility surface dynamics , 2006 .

[23]  H. Zou.  The Adaptive Lasso and Its Oracle Properties , 2006 .

[24]  M. Yuan,et al.  Model selection and estimation in regression with grouped variables , 2006 .

[25]  Domenico Giannone,et al.  Bayesian VARs with Large Panels , 2007 .

[26]  Chih-Ling Tsai,et al.  Regression coefficient and autoregressive order shrinkage and selection via the lasso , 2007 .

[27]  Karim Lounici.  Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators , 2008, 0801.4610.

[28]  D. Giannone,et al.  Large Bayesian VARs , 2008, SSRN Electronic Journal.

[29]  M. Pesaran,et al.  Infinite Dimensional VARs and Factor Models , 2009, SSRN Electronic Journal.

[30]  E. Mammen,et al.  Time Series Modelling With Semiparametric Factor Dynamics , 2007 .

[31]  Massimiliano Pontil,et al.  Taking Advantage of Sparsity in Multi-Task Learning , 2009, COLT.

[32]  P. Bickel,et al.  SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR , 2008, 0801.1095.

[33]  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.

[34]  Junzhou Huang,et al.  The Benefit of Group Sparsity , 2009 .

[35]  Wolfgang Härdle,et al.  High Dimensional Nonstationary Time Series Modelling with Generalized Dynamic Semiparametric Factor Model , 2010 .

[36]  Dietmar Fehr,et al.  Exclusion in the All-Pay Auction: An Experimental Investigation , 2010 .

[37]  W. Härdle,et al.  Localising Temperature Risk , 2010 .

[38]  Markus Reiß,et al.  Estimation of the characteristics of a Lévy process observed at arbitrary frequency , 2010 .

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

[40]  Lydia Mechtenberg,et al.  A Strategic Mediator Who is Biased into the Same Direction as the Expert Can Improve Information Transmission , 2010 .

[41]  Alexander Meyer-Gohde.  Sticky Information and Determinacy , 2011 .

[42]  Salmai Qari,et al.  The Law of Attraction Bilateral Search and Horizontal Heterogeneity , 2011 .

[43]  Y. Rozenholc,et al.  Pointwise adaptive estimation for quantile regression , 2011 .

[44]  Sigbert Klinke.  Developing web-based tools for the teaching of statistics: Our Wikis and the German Wikipedia , 2011 .

[45]  U. Bindseil,et al.  The Basel III framework for liquidity standards and monetary policy , 2011 .

[46]  Markus Reiß,et al.  Asymptotic equivalence and sufficiency for volatility estimation under microstructure noise , 2010, 1001.3006.

[47]  Yuichi Mori,et al.  How Computational Statistics Became the Backbone of Modern Data Science , 2011 .

[48]  Juliane Scheffel.  How Do Unusual Working Schedules Affect Social Life? , 2011 .

[49]  W. Härdle,et al.  A Confidence Corridor for Sparse Longitudinal Data Curves , 2011 .

[50]  Risk Patterns and Correlated Brain Activities , 2011 .

[51]  News-driven Business Cycles in SVARs , 2011 .

[52]  W. Härdle,et al.  A Confidence Corridor for Expectile Functions , 2011 .

[53]  Hauke R. Heekeren,et al.  The Neural Basis of Following Advice , 2011, PLoS biology.

[54]  Santiago Moreno-Bromberg,et al.  Pollution Permits, Strategic Trading and Dynamic Technology Adoption , 2011 .

[55]  N. Hautsch,et al.  Predicting Bid-Ask Spreads Using Long Memory Autoregressive Conditional Poisson Models , 2011 .

[56]  Song Song.  Dynamic Large Spatial Covariance Matrix Estimation in Application to Semiparametric Model Construction via Variable Clustering: the SCE approach , 2011, 1106.3921.

[57]  Soyoung Q. Park,et al.  Neurobiology of Value Integration: When Value Impacts Valuation , 2011, The Journal of Neuroscience.

[58]  Juliane Scheffel.  Identifying the Effect of Temporal Work Flexibility on Parental Time with Children , 2011 .

[59]  Juliane Scheffel.  Compensation of Unusual Working Schedules , 2011 .

[60]  Russ Moro,et al.  Forecasting Corporate Distress in the Asian and Pacific Region , 2011 .

[61]  Asymptotics of Asynchronicity , 2011, 1106.4222.

[62]  U. Bindseil.  The economics of TARGET2 balances , 2011 .

[63]  W. Härdle,et al.  Mean Volatility Regressions , 2011 .

[64]  Ru Xie.  Human Capital Formation on Skill-Specific Labor Markets , 2011 .

[65]  Fang Yao.  Monetary Policy, Trend Inflation and Inflation Persistence , 2011 .

[66]  C. Scarpa,et al.  The regulation of interdependent markets , 2011 .

[67]  Sara van de Geer,et al.  Statistics for High-Dimensional Data: Methods, Theory and Applications , 2011 .

[68]  Wolfgang Karl Härdle,et al.  Bayesian Networks and Sex-Related Homicides , 2011 .

[69]  M. Gilli,et al.  Bargaining and Collusion in a Regulatory Model , 2011 .

[70]  Xiaolian Liu,et al.  Can crop yield risk be globally diversified , 2011 .

[71]  Anthony R'eveillac,et al.  CRRA utility maximization under risk constraints , 2011, 1106.1702.

[72]  Markus Bibinger,et al.  An estimator for the quadratic covariation of asynchronously observed Itô processes with noise: Asymptotic distribution theory , 2011 .

[73]  M. Burda,et al.  What Explains the German Labor Market Miracle in the Great Recession? , 2011, SSRN Electronic Journal.

[74]  R. Herrera,et al.  Extreme value models in a conditional duration intensity framework , 2011 .

[75]  A. Werwatz,et al.  An Indicator for National Systems of Innovation: Methodology and Application to 17 Industrialized Countries , 2011 .

[76]  Dieter Nautz,et al.  The Information Content of Central Bank Interest Rate Projections: Evidence from New Zealand , 2012 .

[77]  Sören Preibusch,et al.  Unwillingness to Pay for Privacy: A Field Experiment , 2011, SSRN Electronic Journal.

[78]  T. S. Adams,et al.  National Bureau of Economic Research, Inc. , 1920, Quarterly Publications of the American Statistical Association.

[79]  H. Frydman,et al.  Modeling the Effect of Macroeconomic Factors on Corporate Default and Credit Rating Transitions , 2006 .

[80]  Wolfgang Härdle,et al.  Spatial Risk Premium on Weather Derivatives and Hedging Weather Exposure in Electricity , 2011 .

[81]  Wolfgang K. Härdle,et al.  Difference Based Ridge and Liu Type Estimators in Semiparametric Regression Models , 2011, J. Multivar. Anal..

[82]  Dieter Nautz,et al.  Short‐Term Herding of Institutional Traders: New Evidence from the German Stock Market , 2013 .

[83]  Wolfgang Härdle,et al.  Oracally Efficient Two-Step Estimation of Generalized Additive Model , 2011 .