Nowcasting German GDP: Foreign factors, financial markets, and model averaging

被引:9
作者
Andreini, Paolo [1 ]
Hasenzagl, Thomas [2 ,3 ]
Reichlin, Lucrezia [4 ,5 ]
Senftleben-Koenig, Charlotte [6 ]
Strohsal, Till [7 ,8 ]
机构
[1] RavenPack Int SL, Marbella, Spain
[2] Univ Minnesota, Minneapolis, MN USA
[3] Fed Reserve Bank Minneapolis, Minneapolis, MN USA
[4] London Business Sch, London, England
[5] Now Casting Econ, London, England
[6] German Fed Minist Econ Affairs & Climate Act, Berlin, Germany
[7] German Fed Chancellery, Berlin, Germany
[8] Free Univ Berlin, Dept Econ, Berlin, Germany
关键词
Nowcasting; Dynamic Factor Model; News index; German national accounts; State space models; Multivariate time series; Macroeconomic forecasting; FORECASTS;
D O I
10.1016/j.ijforecast.2021.11.009
中图分类号
F [经济];
学科分类号
02 ;
摘要
This paper develops a nowcasting model for the German economy. The model out-performs a number of alternatives and produces forecasts not only for GDP but also for other key variables. We show that the inclusion of a foreign factor improves the model's performance, while financial variables do not. Additionally, a comprehensive model averaging exercise reveals that factor extraction in a single model delivers slightly better results than averaging across models. Finally, we estimate a "news"index for the German economy in order to assess the overall performance of the model beyond forecast errors in GDP. The index is constructed as a weighted average of the nowcast errors related to each variable included in the model.(c) 2021 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码:298 / 313
页数:16
相关论文
共 32 条
[11]  
Bragoli Daniela., 2015, OECD J J BUSINESS CY, V2015, P5
[12]  
CARSTENSEN K., 2009, ifo Schnelldienst, V62, P15
[13]   Macroeconomic news and market reaction: Surprise indexes meet nowcasting [J].
Caruso, Alberto .
INTERNATIONAL JOURNAL OF FORECASTING, 2019, 35 (04) :1725-1734
[14]   Nowcasting with the help of foreign indicators: The case of Mexico [J].
Caruso, Alberto .
ECONOMIC MODELLING, 2018, 69 :160-168
[15]  
Cascaldi-Garcia D., 2021, INT FINANCE DISCUSSI
[16]  
Cimadomo J., 2020, EUROPEAN CENTRAL BAN
[17]  
DAgostino A., 2013, OECD J J BUSINESS CY, V2012, P21
[18]   A QUASI-MAXIMUM LIKELIHOOD APPROACH FOR LARGE, APPROXIMATE DYNAMIC FACTOR MODELS [J].
Doz, Catherine ;
Giannone, Domenico ;
Reichlin, Lucrezia .
REVIEW OF ECONOMICS AND STATISTICS, 2012, 94 (04) :1014-1024
[19]   A two-step estimator for large approximate dynamic factor models based on Kalman filtering [J].
Doz, Catherine ;
Giannone, Domenico ;
Reichlin, Lucrezia .
JOURNAL OF ECONOMETRICS, 2011, 164 (01) :188-205
[20]   The generalized dynamic-factor model: Identification and estimation [J].
Forni, M ;
Hallin, M ;
Lippi, M ;
Reichlin, L .
REVIEW OF ECONOMICS AND STATISTICS, 2000, 82 (04) :540-554