Polls to probabilities: comparing prediction markets and opinion polls

Reade, J.J. and Vaughan Williams, L. ORCID: 0000-0002-9639-9217, 2019. Polls to probabilities: comparing prediction markets and opinion polls. International Journal of Forecasting, 35 (1-2), pp. 336-350. ISSN 0169-2070

Preview

Text 11278_Vaughan-Williams.pdf - Pre-print Download (2MB) | Preview

Abstract

The forecasting of election outcomes is a hugely popular activity, and not without reason: the outcomes can have significant economic impacts, for example on stock prices. As such, it is economically important, as well as of academic interest, to determine the forecasting methods that have historically performed best. However, the forecasts are often incompatible, as some are in terms of vote shares while others are probabilistic outcome forecasts. This paper sets out an empirical method for transforming opinion poll vote shares into probabilistic forecasts, and then evaluates the performances of prediction markets and opinion polls. We make comparisons along two dimensions, bias and precision, and find that converted opinion polls perform well in terms of bias, while prediction markets are good for precision.

Item Type:	Journal article
Publication Title:	International Journal of Forecasting
Creators:	Reade, J.J. and Vaughan Williams, L.
Publisher:	Elsevier
Date:	2019
Volume:	35
Number:	1-2
ISSN:	0169-2070
Identifiers:	Number Type 10.1016/j.ijforecast.2018.04.001 DOI
Divisions:	Schools > Nottingham Business School
Record created by:	Linda Sullivan
Date Added:	05 Jun 2018 13:33
Last Modified:	24 May 2022 14:41
URI:	https://irep.ntu.ac.uk/id/eprint/33821

Actions (login required)

Edit View

Views

Downloads