The comparative accuracy of judgmental and model forecasts of American football games

39Citations
Citations of this article
55Readers
Mendeley users who have this article in their library.
Get full text

Abstract

This paper compares the forecasts of the outcomes of NFL games made by 31 statistical models with those of 70 experts who predicted the winners of 496 NFL games played in the 2000 and 2001 seasons. We also analyze the betting line predictions. There are nearly 18,000 expert and 12,000 statistical forecasts. The difference in the accuracy of the experts and statistical systems in predicting game winners was not statistically significant. The variation in the success rates was higher among experts than statistical systems, but the betting line outperformed both. Moreover, having more information did not always improve the forecasting accuracy. Neither the experts nor the systems could profitably beat the betting line. © 2007 International Institute of Forecasters.

Cite

CITATION STYLE

APA

Song, C. U., Boulier, B. L., & Stekler, H. O. (2007). The comparative accuracy of judgmental and model forecasts of American football games. International Journal of Forecasting, 23(3), 405–413. https://doi.org/10.1016/j.ijforecast.2007.05.003

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free