|
Activity Number:
|
474
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #308403 |
|
Title:
|
Performance Comparison of Simple Forecasting Methods for Macroeconomic Indicators
|
|
Author(s):
|
Bogong T. Li*+
|
|
Companies:
|
Bank of America
|
|
Address:
|
100 N Tryon St, Charlotte, NC, 28255,
|
|
Keywords:
|
Economic indicators ; Forecast ; Exponential smoothing ; Stepwise regression ; Holt-Winters
|
|
Abstract:
|
Monthly economic indicators released by U.S. federal government impact financial markets the most when the direction of their change is different from market consensus. For those who have anticipated the difference will achieve significant financial gain. Given current quantitative forecast methods based on statistical models minimize only squared errors, irrespective to directional differences, optimal MSE models do not necessary produce the best forecasts. In this research we will evaluate the relationship between MSE types of criteria with directional correction using forecasts for some important U.S. macroeconomic monthly releases. As a result from this evaluation, we further propose an improved forecasting method that will perform better in forecasting direction than current methods.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
