Pre-race behaviour of horses as a predictor of race finishing order
Publication Type: |
Journal Article |
Year of Publication: |
1997 |
Authors: |
G. D. Hutson, M. J. Haskell |
Publication/Journal: |
Applied Animal Behaviour Science |
Keywords: |
gambling, horse, pre-race behaviour |
Abstract:
The behaviour and appearance of 867 horses entered in 67 races at two Melbourne racecourses, Flemington and Moonee Valley, was assessed over a 20-month period. We recorded 29 variables for each horse, 19 of which were behaviour/appearance variables. Fourteen variables were recorded in the parade ring/mounting yard as the horse was being led by the groom prior to the race, and five variables were scored while the horse was on the way to the starting gate with the jockey up. Seven variables were race-book information, and three variables were recorded from the published race results: actual weight carried; starting price; and finishing order. The data were analysed using the techniques of univariate and bivariate analysis, and multivariate discriminant analysis.
Univariate analysis showed that only tail elevation (P < 0.05), neck angle with the jockey up (P < 0.01), and resistance to the bit (P < 0.05) had a significant relationship with finishing order. However, the power of these variables to discriminate finishing order was poor when compared with the traditional variables of starting price (P < 0.001) and weight carried (P < 0.001). Classification of horses into winners (finishing in the first 20-percentile) and losers (finishing in the last 20-percentile) showed that winners tended to be fitter and more relaxed and losers tended to be more aroused and required greater control. Bivariate analysis confirmed that increased elevation of the head, neck and tail were associated with increased arousal. Bivariate analysis also suggested that sweating on its own was not a reliable performance indicator, but in conjunction with other variables might indicate losers. Multivariate discriminant analysis was used to discriminate winners (horses finishing in the first 20-percentile) from other horses, and losers (last 20-percentile) from other horses. The data were selected for analysis on the basis of performance at Moonee Valley, and then the computed discriminant functions were used to predict group membership (i.e. winners or losers) at Flemington. All variables were entered into the analysis using a stepwise method. Six variables were required for maximum discrimination of losers, in contrast with eleven variables required for discrimination of winners. Classification results using the discriminant functions to predict winners and losers showed that (67.4%) losing predictions were correct. In contrast, only (28.1%) winning predictions were correct. We conclude that pre-race behaviour and appearance of horses is a valuable aid in predicting losing horses and that this information has potentially high economic worth.