<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Ordinal regression models are frequently used in academic literature to model outcomes of soccer matches, and seem to be preferred over nominal models. One reason is that, obviously, there is a natural hierarchy of outcomes, with victory being preferred to a draw and a draw being preferred to a loss. However, the often used ordinal models have an assumption of proportional odds: the influence of an independent variable on the log odds is the same for each outcome. This paper illustrates how ordinal regression models therefore fail to fully utilize independent variables that contain information about the likelihood of matches ending in a draw. However, in practice, this flaw does not seem to have a substantial effect on the predictive accuracy of an ordered logit regression model when compared to a multinomial logistic regression model.</p></abstract>

Ordinal regression models are frequently used in academic literature to model outcomes of soccer matches, and seem to be preferred over nominal models. One reason is that, obviously, there is a natural hierarchy of outcomes, with victory being preferred to a draw and a draw being preferred to a loss. However, the often used ordinal models have an assumption of proportional odds: the influence of an independent variable on the log odds is the same for each outcome. This paper illustrates how ordinal regression models therefore fail to fully utilize independent variables that contain information about the likelihood of matches ending in a draw. However, in practice, this flaw does not seem to have a substantial effect on the predictive accuracy of an ordered logit regression model when compared to a multinomial logistic regression model.

Ordinal versus nominal regression models and the problem of correctly predicting draws in soccer

International Journal of Computer Science in Sport

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Ordinal regression models are frequently used in academic literature to model outcomes of soccer matches, and seem to be preferred over nominal models. One...

Ordinal versus nominal regression models and the problem of correctly predicting draws in soccer

Published Online: Jul 22, 2017

Page range: 50 - 64

DOI: https://doi.org/10.1515/ijcss-2017-0004

Keywords
association football, forecasting, ordered regression

© 2017 Hvattum, L. M., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Ordinal versus nominal regression models and the problem of correctly predicting draws in soccer

Published Online: Jul 22, 2017

Page range: 50 - 64

DOI: https://doi.org/10.1515/ijcss-2017-0004

Keywordsassociation football, forecasting, ordered regression

© 2017 Hvattum, L. M., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
association football, forecasting, ordered regression