Embrace the Differences: Revisiting the Pollyvote Method of Combining Forecasts for U.S. Presidential Elections (2004 to 2020)

17 Pages Posted: 8 Jul 2021 Last revised: 4 Oct 2021

See all articles by Andreas Graefe

Andreas Graefe

Macromedia University of Applied Sciences

Date Written: October 4, 2021

Abstract

While combining forecasts is well-known to reduce error, the question of how to best combine forecasts remains. Prior research suggests that combining is most beneficial when relying on diverse forecasts that incorporate different information. Here I provide evidence in support of this hypothesis by analyzing data from the PollyVote project, which has published combined forecasts of the popular vote in U.S. presidential elections since 2004. Prior to the 2020 election, the PollyVote revised its original method of combining forecasts by, first, restructuring individual forecasts based on their underlying information and, second, adding naïve forecasts as a new component method. On average across the last 100 days prior to the five elections from 2004 to 2020, the revised PollyVote reduced the error of the original specification by eight percent and, with a mean absolute error of 0.8 percentage points, was more accurate than any of its component forecasts. The results suggest that, when deciding about which forecasts to include in the combination, forecasters should be more concerned about the component forecasts’ diversity than their historical accuracy.

Keywords: forecasting, combining, polls, betting markets, citizen forecasts, models

JEL Classification: C53

Suggested Citation

Graefe, Andreas, Embrace the Differences: Revisiting the Pollyvote Method of Combining Forecasts for U.S. Presidential Elections (2004 to 2020) (October 4, 2021). International Journal of Forecasting, Forthcoming, Available at SSRN: https://ssrn.com/abstract=3871059 or http://dx.doi.org/10.2139/ssrn.3871059

Andreas Graefe (Contact Author)

Macromedia University of Applied Sciences ( email )

Sandstrasse 9
Munich, Bavaria 80337
Germany

HOME PAGE: http://www.andreas-graefe.org

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
60
Abstract Views
371
Rank
678,601
PlumX Metrics