Erasmus university rotterdam
Download 1.62 Mb.
|
- Navigate this page:
- Is there a favorite longshot bias in ATP and WTA tennis’
- Table 21: Hypotheses evaluation
ConclusionIn this study the matches of all the ATP and WTA tournaments of the years 2009 to 2013 are examined. Before we evaluate the hypotheses and conclusion of the results of section 5, we will restate the research question and the hypotheses. The research question which is answered in this thesis was: ‘Is there a favorite longshot bias in ATP and WTA tennis?’ Hypotheses: H1: There exists a favorite longshot bias in ATP and WTA tennis. H2: The favorite longshot bias is stronger in women tournaments. H3a: The favorite longshot bias is becoming stronger over the years. H3b: The favorite longshot bias is becoming stronger over the years in ATP tournaments. H3c: The favorite longshot bias is becoming stronger over the years in WTA tournaments. H4a: At gravel tournaments occurs a stronger favorite longshot bias than in hard-court tournaments. H4b: At gravel tournaments occurs a stronger favorite longshot bias than in hard-court tournaments in ATP tournaments. H4c: At gravel tournaments occurs a stronger favorite longshot bias than in hard-court tournaments in WTA tournaments. To answer the question the odds of WTA and ATP tennis tournaments from 2009 to 2013 were analyzed. The odds were calculated into winning probabilities and divided over 20 probability categories. For every category the mean return and standard deviation was calculated. For every category we did a T-test, where the results lower than -2 or higher than 2 are significant, obviously -2 < t < 2 is insignificant. Table 21: Hypotheses evaluation
Looking at the results of all the data together in 5.1 and the results of ATP and WTA separately in 5.2 we see many significant t-values and the mean return of favorites is often higher than underdogs. At first sight, you see a clear favorite longshot bias in both situations. However, in section 5.3.2 and 5.4.2, we separate the ATP and WTA tournament over the years and per surface, which lead to many insignificant results. This means that if we look at the results of all the data together, it looks all good and significant, but if we separate it, it does not look that significant anymore. In addition, if we look at the t-values in the results overall and sorted by gender, we see many significant t-values in underdogs categories (1 to 7), which is a good indication of a favorite longshot bias. However, in the favorite categories (15 to 20) we also see many significant t-values. Based on this, we made the conclusion that there is no strong favorite longshot bias in ATP and WTA tournaments over 2009 to 2013. This is not in line with the literature of Forrest & Mchale, 2007 and Cain et al, 2003. Only at hard-court (o) tournaments in ATP tournaments and in 2011 ATP tournaments, we see significant t-values. However, this is such a small share that we conclude that there is no favorite longshot bias in ATP and WTA tournament over the years or per surface. Articles that investigate the favorite longshot bias in tennis before, found a favorite longshot bias (Forrest & Mchale, 2007 and Cain et al, 2003). There were no tennis-related articles which found a absent of a favorite longshot bias. In other sports, there were articles which did not found a favorite longshot bias like; Busche & Hall 1988 (horse racing), Busche & Walls 2000 (racetrack), Vaughan Williams & Paton 1998 (horse racing), Woodland & Woodland 1994 (baseball) and Woodland & Woodland 2001 (hockey). The results of this study are corresponding to those contradicting literature.f The answer to the question is as follows: ‘No, a favorite longshot bias in tennis ATP and WTA tennis does not exists. There are only indication for a favorite longshot bias in 2011 ATP tournaments and ATP hard-court (i) tournaments. However, the overall conclusion is that there is an absent of a favorite longshot bias in ATP and WTA tennis (sorted by gender, years and surface)’. In the next section, the contribution and limitations of this study are discussed. In addition, some interesting directions for future research are discussed.
|