Erasmus university rotterdam
Download 1.62 Mb.
|
Results over the years5.3.1 Results over the years - ATP and WTA tournamentsAfter looking at the difference between men and women in the previous section, this section will show results over the last 5 years separately. Table 9: Results of all ATP and WTA tournaments sorted by year (2009-2013)
In the tables above, the pattern of the less negative return in the higher categories and the higher negative return in the lower categories still emerges. Graph 3: Development of the mean return of ATP and WTA tournaments in the last 5 years (2009-2013) Graph 3 shows the line of the mean returns per year. It is hard to see which favorite longshot bias is the strongest, but in every year there the line goes upwards. In category 1 in 2013 there is a positive return of €0,090. In this category there are 39 matches and one match is won by an underdog which gives a high return and therefore the mean return is positive. Also category 8, 10 and 17 of 2013 matches will give you a positive return. The favorite longshot bias is based on underdogs and favorites, which means we have to look at category 1 (underdogs) and category 20 (favorites). In table 10 a quick overview of the returns is added. In every year, except of 2013, the return in category 20 is higher than in category 1. Based on these facts, you might be able to conclude that, a favorite longshot bias exists in every year, except of 2013. Table 10: Mean return in category 1-7 and 15-20 over the years
Looking at table 10, we see that for every year the underdog categories generate a lower mean return than the favorite categories, except of 2012. Based on those numbers, you might be able to conclude that, a favorite longshot bias exists in every year, except of 2012. It is hard to look if the trend is becoming stronger over the years. If you look at the categories 1-7 the return gets lower till 2011 and from there the return gets higher. In the favorite categories the return till 2011 becomes higher, but in 2012 there is a very low result of -0,231. The results are not showing a clear trend over the years. If we compare the t-values in the years with the t-values of section 5.1 and 5.2, we see a lot more insignificant results. Because of those insignificant t-values (-2 < t < 2) we can doubt about the existence of a favorite longshot bias. It is interesting to test the ATP and WTA tournaments separately, because this might lead better t-values. With better t-values the doubt about the existence of a favorite longshot bias could disappear. In 5.3.2 we test the data over the years for ATP and WTA tournaments separately. Directory: pub pub -> Project Scoring Template Pre-Construction Phase New Core/Branch Campus Projects pub -> Acm word Template for sig site pub -> The german unification, 1815-1870 pub -> Baltic Olympiads in Informatics: Challenges for Training Together pub -> Preparation of Papers for ieee transactions on medical imaging pub -> Forthcoming meetings and conferences pub -> Asilomar Conference on Circuits, Systems & Computers, Pacific Grove, ca, November 1978, pp. 55 58 pub -> Forthcoming meetings and conferences pub -> Harmonised compatibility and sharing conditions for video pmse in the 7 9 ghz frequency band, taking into account radar use Download 1.62 Mb. Share with your friends:
|