|
Activity Number:
|
274
- Macroeconomic Forecasting and Policy in Data Rich Digital Age Environments
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #300382
|
|
|
Title:
|
Google Trends and the Macroeconomy: a Bayesian Mixed Frequency Approach
|
|
Author(s):
|
Arnab Bhattacharjee* and David Kohns
|
|
Companies:
|
Heriot-Watt University and Heriot-Watt University
|
|
Keywords:
|
|
|
Abstract:
|
This paper investigates the use of Google Trends for structural macroeconomic forecasting. An issue when dealing with Google Trends for forecasting is that of mixed frequency and high dimensionality. We provide structural mixed frequency frameworks as well as econometric frameworks which are able to deal with these issues. We synthesise the presented methods into one estimator, the Bayesian Structural Time Series model augmented MIDAS (BSTS-U-MIDAS), which is able to address both issues and uncover the economic relationship of high frequency variables to the low frequency target variable. We find that the estimator beats all other mixed frequency estimators and that Google Trends increase forecasting fit. This provides promising results for structural modeling using Google Trends.
|
Authors who are presenting talks have a * after their name.
