CONSISTENCY IN THE US CONGRESSIONAL POPULAR OPINION POLLS AND PREDICTION MARKETS

Main Article Content

Eliot Tonkes
Dharma Lesmono

Abstract

Prediction and betting markets have evolved with contracts based on electoral outcomes and the traded prices provide a measure of speculators’ views on electoral outcomes. Conversely, popular opinion polls yield data which provide statistics on the public’s declared voting intentions. This article formulates a model to describe the stochastic evolution of opinion polls, and the resultant probability distribution of seats won in the US House of Congress. Based on standard methods from financial option pricing theory, we can then determine the theoretical value of observed contracts in the prediction markets. Our results show that qualitative predictions are obeyed, but there exist significant deviations between the actual prices traded in the Iowa Electronic Market (IEM) and our theoretical valuation under real-world expectations. Some explanations are provided, which are consistent with conclusions drawn by other authors who have studied electoral prediction markets.

Article Details

Section
Articles

References

C. Bialik Grading the pollsters, The Wall Street Journal (Dow Jones), 15 November 2006.

L.B. Brown and H.W. Chappell Jr. “Forecasting presidential elections using history and polls”. International Journal of Forecasting (1999) 15 127–135.

A.R. Chowdhury “Political Surfing over Economic Waves : Parliamentary Election Timing in India” American Journal of Political Science (1993) 37 1100–1118.

R. Eisinga, P.H. Franses, and M. Ooms. “Forecasting long memory left-right political orientations” International Journal of Forecasting (1999) 15 185–199.

Robert S. Erikson and Christopher Wlezein. “Are Political Markets Really Superior to Polls as Election Predictor?” Public Opinion Quarterly (2008) 72 190-215.

Robert S. Erikson and Christopher Wlezein.”Markets vs. Polls as Predictors: An Historical Assesment of US Presidential Elections” Paper presented at the Annual Meeting of the American Association for Public Opinion Research, Hollywood, Florida, May 209.

T.M. Holbrook and J.A. DeSart “Using state polls to forecast presidential election outcomes in the American states”. International Journal of Forecasting, (1999) 15 137–142.

T. Ito “The Timing of Elections and Political Business Cycles in Japan”. Journal of Asian Economics (1990) 1 135–156.

Z.M. Kmietowicz. “Sampling Errors in Political Polls”. Teaching Statistics (1994) 16 70-74.

D. Lesmono, E.J. Tonkes, and K. Burrage. “An early political election problem”. ANZIAM Journal, (2003) 45E C16–C33.

Dharma Lesmono “A Term Structured Volatility Model of Poll Data and Its Application to Election Timing”, in Aspects of Mathematical Modelling (eds. R.J. Hosking and E. Venturino), (Basel, Birkhauser Verlag, 2008) at pp 283-291.

Lionel Page “Comparing Prediction Market Prices and Opinion Polls in Political Elections”, Journal of Prediction Markets (2008) 2 91-97.

Paul W. Rhode and Koleman S Strumpf “Historical Presidential Betting Markets”, The Journal of Economic Perspectives (2004) 18 127-142.

A.J. Roberts, Elementary Calculus of Financial Mathematics. (Philadelphia, SIAM Mathematical Modeling ad Computation, 2009).

D. Rothschild “Forecasting Elections Comparing Prediction Markets, Polls, and Their Biases”, Public Opinion Quarterly (2009) 73 895-916.

Smith “Endogenous Election Timing in Majoritarian Parliamentary Systems”. Economics and Politics (2006) 8 85–110.

Smith, “Election Timing in Majoritarian Parliaments”. British Journal of Political Science (2003) 33 397–418.

Smith, Election Timing. (Cambridge, Cambridge University Press, 2004).