Ricardo Manuel Santos

Using data from all FIFA World Cup competitions that took place between 1994 and 2014, a step logit model is estimated to forecast the likelihood of success of each team in each tournament. The model correctly identifies the winner in five out of the six tournaments, and among many variables considered, key contributors to the model’s forecasting performance are identified. Using only the information available by the date preceding each of the last two in-sample World Cups, we can perform a more ambitious test of the model’s ability to forecast the winner at future tournaments. Our results...Read more

David Forrest

Manipulation of on-field events for betting gain appears to be a growing problem in football and other sports. It can be linked to developments in the betting environment and is a potential threat to the football industry to the extent that it may deter fans, sponsors, and broadcasters from purchasing the product. Risks are highest in European lower-tier competitions where high liquidity in the betting market contrasts with modest incomes among players and officials. The liquidity is provided principally by Asian betting markets that are largely unregulated, which itself is a significant...Read more

Rodney J. Paul
Andrew P. Weinbach

The National Basketball Association (NBA) and National Hockey League (NHL) are studied to ascertain the determinants of betting volume on an individual game-to-game basis. Actual betting volume was obtained and aggregated across three on-line sportsbooks for the 2008-09 season. Independent variables such as the quality of teams, television coverage by network, day of the week, time of day, month of the season, etc. are included in a regression model to determine the factors that influence betting volume. The results reveal betting behavior is much like fan behavior as key fan-attributes,...Read more