Many people commenting on Taiwan 2012 have cited the Chengchi/XFuture exchange market’s measures of candidate support levels. Given widespread skepticism about substantial variation and idiosyncrasies in Taiwanese media polls, it is not surprising that people have been casting around for more reliable numbers.

A further reason for the popularity of the election market in this campaign is that it has consistently reported optimistic numbers for Tsai Ing-wen; the favoured candidate for many in the English language blogosphere. Whereas blue friendly media polls have given Ma a lead of between 4 and 10 points consistently throughout the campaign, the election market has had Tsai ahead (on occasion by a large margin). The XFuture website features markets for individual components of the candidates’ platforms, support levels among different segments of the electorate, and for individual legislative districts. As a companion to the campaigns for interested observers it is terrific.

But are the numbers meaningful? Who should we believe when there is a near-20 point difference between the media polls (Ma ahead handily) and the prediction market (Tsai well ahead)? With exquisite timing several Taiwanese political scientists have just published a paper in the Journal of Prediction Markets (yes, there is a journal for everything). The paper is available here ($). I take the liberty of pasting the abstract below:

“This paper devises a methodology to compare the accuracy of prediction markets and polls. The data of the Exchange of Future Events (xFuture) for Taiwan’s 2006 mayoral elections and 2008 presidential election show that the prediction markets outperform the opinion polls in various indices of accuracy. In terms of the last forecast before the election date, the accuracy of the prediction markets is 3 to 10 percent higher than that of the opinion polls. When comparing the accuracy of historical forecasts, the prediction markets outperform the polls in 93 to 100 percent of the cases. Moreover, the average accuracy of the prediction markets is 9 to 10 percent higher than that of the polls, with a standard deviation more than 2 percent less than that of the polls. To examine the robustness of these comparisons, this paper conducts two tests including daily forecast and normalized accuracy, and finds that the prediction markets successfully pass the tests with a significantly better accuracy than the polls.”

Click here for the latest market conditions for the presidential candidates.

Mail me at jonathan.sullivan@nottingham.ac.uk, follow me on Twitter @jonlsullivan, or access my papers at http://jonlsullivan.com