J. James Reade

Information and Efficiency: Goal Arrival in Soccer Betting

In an efficient market news is incorporated into prices rapidly and completely. Attempts to test for this in financial markets have been undermined by the possibility of information leakage unobserved by the econometrician. An alternative is to switch to laboratory conditions, at the price of some artificiality. Potentially, sports betting markets offer a superior way forward: assets have terminal values and news can break remarkably cleanly, as when a goal is scored in soccer. We exploit this context to test for efficiency, applying a novel identification strategy to high-frequency data. On our evidence, prices update swiftly and fully.

Punishing the Foreigner: Implicit Discrimination in the Premier League Based on Oppositional Identity*

We present the first empirical study to reveal the presence of implicit discrimination in a non-experimental setting. By using a large dataset of in-match data in the English Premier League, we show that white referees award significantly more yellow cards against non-white players of oppositional identity. We argue that this is the result of implicit discrimination by showing that this discriminatory behaviour: (i) increases in how rushed the referee is before making a decision, and (ii) it increases in the level of ambiguity of the decision. The variation in (i) and (ii) cannot be explained by any form of conscious discrimination such as taste-based or statistical discrimination. Moreover, we show that oppositional identity players do not differ in their behaviour from other players along several dimensions related to aggressiveness and style of play providing further evidence that this is not statistical discrimination.

Linear vs. Log‐linear Unit‐Root Specification: An Application of Mis‐specification Encompassing*

The objective of this paper is to apply the mis‐specification (M‐S) encompassing perspective to the problem of choosing between linear and log‐linear unit‐root models. A simple M‐S encompassing test, based on an auxiliary regression stemming from the conditional second moment, is proposed and its empirical size and power are investigated using Monte Carlo simulations. It is shown that by focusing on the conditional process the sampling distributions of the relevant statistics are well behaved under both the null and alternative hypotheses. The proposed M‐S encompassing test is illustrated using US total disposable income quarterly data.

FORECASTING WITH SOCIAL MEDIA: EVIDENCE FROM TWEETS ON SOCCER MATCHES

Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8 million posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a microblogging dictionary to analyze the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards. (JEL G14, G17)

Prediction Markets, Social Media and Information Efficiency

We consider the impact of breaking news on market prices. We measure activity on the micro‐blogging platform Twitter surrounding a unique, newsworthy and identifiable event and investigate subsequent movements of betting prices on the prominent betting exchange, Betfair. The event we use is the Bigotgate scandal, which occurred during the 2010 UK General Election campaign. We use recent developments in time series econometric methods to identify and quantify movements in both Twitter activity and Betfair prices, and compare the timings of the two. We find that the response of market prices appears somewhat sluggish and is indicative of market inefficiency, as Betfair prices adjust with a delay, and there is evidence for post‐news drift. This slow movement may be explained by the need for corroborating evidence via more traditional forms of media. Once important tweeters begin to tweet, including importantly breaking news Twitter feeds from traditional media sources, prices begin to move.

Simulating Properties of the Likelihood Ratio Test for a Unit Root in an Explosive Second-Order Autoregression

This paper provides a means of accurately simulating explosive autoregressive processes and uses this method to analyze the distribution of the likelihood ratio test statistic for an explosive second-order autoregressive process of a unit root. While the standard Dickey–Fuller distribution is known to apply in this case, simulations of statistics in the explosive region are beset by the magnitude of the numbers involved, which cause numerical inaccuracies. This has previously constituted a bar on supporting asymptotic results by means of simulation, and analyzing the finite sample properties of tests in the explosive region.

The Wisdom of Amateur Crowds: Evidence from an Online Community of Sports Tipsters

We analyse the accuracy of crowd forecasts produced on Oddsportal, an online community of amateur sports tipsters. Tipsters in this community are ranked according to the betting return on their tips, but there are no prizes for accuracy. Nevertheless, we find that aggregated tips in this community contain information not in betting prices. A strategy of betting when a majority predict an outcome produces average returns of 1.317% for 68,339 events. The accuracy of these forecasts stems from the wisdom of the whole crowd, as selecting sections of the crowd based on experience or past forecast accuracy does not improve betting returns.

Combining Prediction Markets and Forecasting Contests

Two popular methods for aggregating individual forecasts are prediction markets, where participants bet on the outcome of future events, and forecasting contests, where participants are ranked according to the accuracy of their forecasts. Can these methods be used in concert to produce more accurate forecasts? We analyse 1.79 million forecasts on oddsportal.com, a social network for sports tipsters. Tipsters are ranked according to the betting return on their tips. We find that an aggregation of these tips predicts sporting outcomes, after controlling for betting/prediction market prices. Rank-order forecasting contests, even without tangible prizes, are useful tools for eliciting crowd forecasts.