Publicação
Performance standards in artistic roller skating
| Resumo: | Figure skating is an increasingly popular sport in Portugal, with a growing number of athletes involved. It is therefore imperative, to closely monitor any anomaly that may exist. The accumulation of data from the championship results and the fact that no studies have been done before with the results of Figure Skating on wheels, makes it an advantage to do it now. Since the Skating judging system is in a transition period, it is important to understand what was the comportment of the last few years, so that it can be compared later with the new system to be implemented. For the development of this dissertation, a problem was identified and analyzed through data mining techniques and statistical tests, in order to achieve results that prove if there is a problem with the current judging system. The overall problem identified was the final results obtained by athletes in European Championships of the last 8 years. As mentioned above, data mining techniques were used, more precisely a sensitivity analysis model was constructed. Data used as input to the sensitivity model and statistical tests were provided by the Federação de Patinagem de Portugal. To define some metrics such as when an athlete’s results are biased, the feedback was collected from coaches and judges. With this dissertation, it was possible to realize that there is a relationship between the final position of the athlete and the place where the championship takes place, as well as the nationality of the judge and the athlete. However, it is not possible to support the origin of the bias identified in the results once it can be unconscious. |
|---|---|
| Autores principais: | Louro, Carolina da Silva |
| Assunto: | Data mining Artistic roller skating Patinagem artística |
| Ano: | 2019 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | ISCTE |
| Idioma: | inglês |
| Origem: | Repositório ISCTE |
| Resumo: | Figure skating is an increasingly popular sport in Portugal, with a growing number of athletes involved. It is therefore imperative, to closely monitor any anomaly that may exist. The accumulation of data from the championship results and the fact that no studies have been done before with the results of Figure Skating on wheels, makes it an advantage to do it now. Since the Skating judging system is in a transition period, it is important to understand what was the comportment of the last few years, so that it can be compared later with the new system to be implemented. For the development of this dissertation, a problem was identified and analyzed through data mining techniques and statistical tests, in order to achieve results that prove if there is a problem with the current judging system. The overall problem identified was the final results obtained by athletes in European Championships of the last 8 years. As mentioned above, data mining techniques were used, more precisely a sensitivity analysis model was constructed. Data used as input to the sensitivity model and statistical tests were provided by the Federação de Patinagem de Portugal. To define some metrics such as when an athlete’s results are biased, the feedback was collected from coaches and judges. With this dissertation, it was possible to realize that there is a relationship between the final position of the athlete and the place where the championship takes place, as well as the nationality of the judge and the athlete. However, it is not possible to support the origin of the bias identified in the results once it can be unconscious. |
|---|