Forecasting Current-Quarter U.S. Exports Using Satellite Data
Author(s) -
Jun Nie,
Amy Oksol
Publication year - 2018
Publication title -
the federal reserve bank of kansas city economic review
Language(s) - English
Resource type - Journals
eISSN - 2163-422X
pISSN - 0161-2387
DOI - 10.18651/er/2q18nieoksol
Subject(s) - quarter (canadian coin) , current (fluid) , satellite , computer science , electrical engineering , geography , engineering , aerospace engineering , archaeology
Forecasting export growth can be challenging. Export growth depends heavily on demand from foreign countries, which is difficult to directly measure. In practice, forecasters usually use growth in foreign gross domestic product. But GDP data are released with a significant delay, and in some economies, GDP is poorly measured. Nighttime lights data from satellites are able to overcome both of these challenges, making them potentially useful in forecasting U.S. exports. {{p}} Jun Nie and Amy Oksol use nighttime lights data to forecast current-quarter U.S. export growth and compare their forecasts to those generated using foreign GDP. They find that forecasts using monthly nighttime lights data outperform those using quarterly foreign GDP. Their results suggest the greater frequency of lights data could help provide increasingly accurate forecasts of export growth.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom