Abstract
The recent expansion of prediction markets provides a great opportunity to test the market efficiency hypothesis and the calibration of trader judgements. Using a large database of observed prices, this article studies the calibration of prediction markets prices on sporting events using both nonparametric and parametric methods. While only minor bias can be observed during most of the lifetime of the contracts, the calibration of prices deteriorates very significantly in the last moments of the contracts’ lives. Traders tend to overestimate the probability of the losing team to reverse the situation in the last minutes of the game.
Acknowledgements
I thank Justin Wolfers, Eric Zitzewitz and Arnaud Maurel for their comments on an earlier version of this article. The usual disclaimer applies.
Notes
1 The money of the transactions may be similar to tokens like on Tradesports which use the term ‘points’ to describe the unit of transactions (10 points = $1).
2 The trader must in particular be supposed to have a level of risk aversion in the range of what has been observed in empirical studies.
3 Or 499 to be more accurate, the last observation giving the final outcome.
4 The presentation of the contract itself having an effect on probability assessment.
5 On a grid of 99 points, the integers from 1 to 99.