Forecasting with large datasets: compressing information before, during or after the estimation?

We study the forecasting performance of three alternative large data forecasting approaches. These three approaches handle the dimensionality problem evoked by a large dataset by compressing its informational content, yet at different stages of the forecasting process. We consider different factor models, a large Bayesian vector autoregression and model averaging techniques, where the data compression takes place before, during and after the estimation of the respective forecasting models. We use a quarterly dataset for Germany that consists of 123 variables and find that overall the large Bayesian vector autoregression and the Bayesian factor augmented vector autoregression provide the most precise forecasts for a set of 11 core macroeconomic variables. Further, we find that the performance of these two models is very robust to the exact specification of the forecasting model.

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

[2]  Rolf Scheufele,et al.  The performance of short-term forecasts of the German economy before and during the 2008/2009 recession , 2012 .

[3]  Halbert White,et al.  Tests of Conditional Predictive Ability , 2003 .

[4]  Klaus Wohlrabe,et al.  Assessing the Macroeconomic Forecasting Performance of Boosting - Evidence for the United States, the Euro Area, and Germany , 2013, SSRN Electronic Journal.

[5]  David H. Small,et al.  Nowcasting: the real time informational content of macroeconomic data releases , 2008 .

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

[7]  Dean Croushore,et al.  Forecasting with Real-Time Macroeconomic Data , 2006 .

[8]  Todd E. Clark,et al.  Bayesian VARs: Specification Choices and Forecast Accuracy , 2011 .

[9]  Frank Schorfheide,et al.  DSGE Model-Based Forecasting , 2012 .

[10]  Christian Schumacher,et al.  Forecasting German GDP Using Alternative Factor Models Based on Large Datasets , 2007, SSRN Electronic Journal.

[11]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

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

[13]  Michele Lenza,et al.  Prior Selection for Vector Autoregressions , 2012, Review of Economics and Statistics.

[14]  T. Berg,et al.  Point and Density Forecasts for the Euro Area Using Bayesian VARs , 2014, SSRN Electronic Journal.

[15]  Jean Boivin,et al.  Monetary Policy in a Data-Rich Environment , 2001 .

[16]  Maik H. Wolters.  Evaluating Point and Density Forecasts of DSGE Models , 2012 .

[17]  Serena Ng,et al.  Determining the Number of Primitive Shocks in Factor Models , 2007 .

[18]  T. Kehoe.  International Macroeconomics Module Code : ECO 00028 M Credits : 10 Term : 2 Contact Hours : 9 two-hour lectures and 4 one-hour seminars ( 22 contact hrs ) Module , 2002 .

[19]  Jonathan H. Wright,et al.  Forecasting U.S. Inflation by Bayesian Model Averaging , 2003 .

[20]  George Kapetanios,et al.  A comprehensive evaluation of macroeconomic forecasting methods , 2019, International Journal of Forecasting.

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

[22]  T. Berg,et al.  Point and Density Forecasts for the Euro Area Using Many Predictors: Are Large BVARs Really Superior? , 2013 .

[23]  Boriss Siliverstovs,et al.  On the Forecasting Properties of the Alternative Leading Indicators for the German GDP: Recent Evidence , 2006 .

[24]  Marco Lippi,et al.  Do Financial Variables Help Forecasting Inflation and Real Activity in the Euro Area , 2002 .

[25]  Peter Christoffersen,et al.  Working Papers Working Papers Working Papers Working Papers Cointegration and Long-horizon Forecasting Cointegration and Long-horizon Forecasting , 2022 .

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

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

[28]  J. Stock,et al.  Forecasting Output and Inflation: The Role of Asset Prices , 2001 .

[29]  Maik H. Wolters,et al.  Forecasting German key macroeconomic variables using large dataset methods , 2014 .

[30]  Christian Schumacher,et al.  Out-of-sample Performance of Leading Indicators for the German Business Cycle: Single vs. Combined Forecasts , 2005 .

[31]  C. Sims,et al.  Bayesian methods for dynamic multivariate models , 1998 .

[32]  Dimitris Korobilis,et al.  VAR Forecasting Using Bayesian Variable Selection , 2009 .

[33]  Christian Schumacher,et al.  Factor Forecasting Using International Targeted Predictors: The Case of German GDP , 2010, SSRN Electronic Journal.

[34]  Christian Schumacher,et al.  POOLING VERSUS MODEL SELECTION FOR NOWCASTING GDP WITH MANY PREDICTORS: EMPIRICAL EVIDENCE FOR SIX INDUSTRIALIZED COUNTRIES , 2013 .

[35]  J. Bai,et al.  Forecasting economic time series using targeted predictors , 2008 .

[36]  Marie Diron,et al.  Short-Term Forecasts of Euro Area Real GDP Growth: An Assessment of Real-Time Performance Based on Vintage Data , 2006, SSRN Electronic Journal.

[37]  A. Timmermann.  Chapter 4 Forecast Combinations , 2006 .

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

[39]  Steffen Henzel,et al.  Prognoseeigenschaften von Indikatoren zur Vorhersage des Bruttoinlandsprodukts in Deutschland , 2013 .

[40]  K. R. Kadiyala,et al.  Numerical Methods for Estimation and Inference in Bayesian VAR-models , 1997 .

[41]  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.

[42]  J. Bai,et al.  Determining the Number of Factors in Approximate Factor Models , 2000 .

[43]  Christian Schumacher,et al.  Forecasting with Factor Models Estimated on Large Datasets: A Review of the Recent Literature and Evidence for German GDP , 2011 .

[44]  Jon Faust,et al.  Comparing Greenbook and Reduced Form Forecasts Using a Large Realtime Dataset , 2007 .

[45]  G. Kapetanios,et al.  Forecasting Large Datasets with Bayesian Reduced Rank Multivariate Models , 2009 .

[46]  J. Stock,et al.  Combination forecasts of output growth in a seven-country data set , 2004 .

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