|
Activity Number:
|
345
- Advances in Macroeconomic Nowcasting and Forecasting: Role of Traditional and Nontraditional Indicators and Big Data
|
|
Type:
|
Topic-Contributed
|
|
Date/Time:
|
Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #317355
|
|
|
Title:
|
Nowcasting GDP in Real Time with a Tone-Adjusted, Time-Varying Layered Topic Model
|
|
Author(s):
|
Jasper de Winter*
|
|
Companies:
|
De Nederlansche Bank
|
|
Keywords:
|
C38;
C8;
E3
|
|
Abstract:
|
We construct a daily sentiment index based on textual information contained in a daily business newspaper. The resulting index traces the business cycle and provides high-frequency information about the type of news that drive or reflect economic fluctuations. Our paper extends earlier work using textual information by investigating the value added of adding hierarchy and time variation to the extracted topics. In an out-of-sample GDP nowcasting exercise, we find that textual newspaper information reduces the forecasting error, indicating news has value over and beyond data releases by statistical agencies.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2021 program
|
