Aim of this diploma thesis is to provide empirical tests of market efficiency of tennis wagering market. In large dataset, which consists of nearly 47 thousands matches and 225 thousands odds, I am searching for anomalies, which can prove market inefficiency. Potentially profitable and exploitable betting strategies are also examined. Main tools of empirical analysis are linear probability models and logit models. Favorit-longshot bias is present in my data, this finding is consistent with results of other empirical works (Lahvička, 2013; Cain, Law, Peel, 2000). Major contribution of this paper is confirmation of home-away bias, the issue, which was not tested in tennis matches so far. The same holds for chart-bias. I am not able to find profitable wagering rules based on out-of-sample predictions of my models. Simple betting rule, which consists of betting systematically on overwhelming favorites, is derived from historical odds. This strategy yields a profit 0,0094, but it's applicability is very limited.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:199722 |
| Date | January 2013 |
| Creators | Flegr, Jan |
| Contributors | Hronza, Martin, Koubek, Ivo |
| Publisher | Vysoká škola ekonomická v Praze |
| Source Sets | Czech ETDs |
| Language | Czech |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0121 seconds