Forecasting with real-time macroeconomic data: The ragged-edge problem and revisions

被引：4
|
作者：
Bouwman, Kees E. [1 ]
Jacobs, Jan P. A. M. [2 ,3 ,4 ]
机构：
[1] Erasmus Univ, Inst Econometr, NL-3000 DR Rotterdam, Netherlands
[2] Univ Groningen, CCSO, NL-9700 AV Groningen, Netherlands
[3] Univ Groningen, Fac Econ & Business, NL-9700 AV Groningen, Netherlands
[4] Australian Natl Univ, CAMA, Canberra, ACT, Australia
来源：
JOURNAL OF MACROECONOMICS | 2011年 / 33卷 / 04期
关键词：
Data revisions; Publication lags; Data imputations; Leading index; State space models; Kalman filter; FACTOR MODEL; GDP; TESTS;
D O I：
10.1016/j.jmacro.2011.04.002
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
Real-time macroeconomic data are typically incomplete for today and the immediate past ('ragged edge') and subject to revision. To enable more timely forecasts the recent missing data have to be imputed. The paper presents a state-space model that can deal with publication lags and data revisions. The framework is applied to the US leading index. We conclude that including even a simple model of data revisions improves the accuracy of the imputations and that the univariate imputation method in levels adopted by The Conference Board can be improved upon. (C) 2011 Elsevier Inc. All rights reserved.
引用
收藏
页码：784 / 792
页数：9
相关论文
共 50 条
12345