Hostname: page-component-77f85d65b8-v2srd Total loading time: 0 Render date: 2026-04-14T13:43:25.284Z Has data issue: false hasContentIssue false

Combining Forecasts for the 2025 German Federal Election: The PollyVote

Published online by Cambridge University Press:  20 February 2025

Andreas Graefe*
Affiliation:
Macromedia University of Applied Sciences, Germany

Abstract

This article presents a forecast for the 2025 German federal election using the PollyVote method, which combines data from polls, expectations, and models to improve predictive accuracy. Building on its application in previous elections, PollyVote highlights the advantages of integrating diverse forecasting approaches while providing insights into their development and performance over time. Three weeks before Election Day, the PollyVote predicts the CDU/CSU will secure the largest vote share at 30.3%, followed by the AfD (20.6%), SPD (17.3%), Greens (12.6%), and the new leftist party BSW (5.1%). The FDP (4.1%) and the Left (3.9%) are forecast to fall short of the 5% threshold required for parliamentary representation. Although the forecasts from individual components show broad agreement, one model that excludes public opinion data diverges, suggesting that polls may overestimate support for the CDU/CSU and underestimate the SPD’s performance.

Information

Type
Forecasting the 2025 Federal German Election
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of American Political Science Association

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

REFERENCES

Erfort, Cornelius, Stoetzer, Lukas F., Gschwend, Thomas, Koch, Elias, Munzert, Simon, and Rajski, Hannah. 2025. “The Zweitstimme Forecast for the German Federal Election 2025.” PS: Political Science & Politics. DOI: 10.1017/S1049096525000150.CrossRefGoogle Scholar
Erikson, Robert S., and Wlezien, Christopher. 2012. The Timeline of Presidential Elections. Chicago: University of Chicago Press.CrossRefGoogle Scholar
Gelman, Andrew, Goel, Sharad, Rivers, Douglas, and Rothschild, David. 2016. “The Mythical Swing Voter.” Quarterly Journal of Political Science 11 (1): 103–30. https://doi.org/10.1561/100.00015031.CrossRefGoogle Scholar
Graefe, Andreas. 2019. “Accuracy of German Federal Election Forecasts, 2013 & 2017.” International Journal of Forecasting 35 (3): 868–77. https://doi.org/10.1016/j.ijforecast.2019.01.004.CrossRefGoogle Scholar
Graefe, Andreas. 2022a. “Combining Forecasts for the 2021 German Federal Election: The PollyVote.” PS: Political Science & Politics 55 (1): 6972. https://doi.org/10.1017/S1049096521000962.Google Scholar
Graefe, Andreas. 2022b. “Combining Forecasts for the 2022 French Presidential Election: The PollyVote.” PS: Political Science & Politics 55 (4): 726–29. https://doi.org/10.1017/S1049096522000555.Google Scholar
Graefe, Andreas. 2023. “Embrace the Differences: Revisiting the PollyVote Method of Combining Forecasts for U.S. Presidential Elections (2004 to 2020).” International Journal of Forecasting 39 (1): 170–77. https://doi.org/10.1016/j.ijforecast.2021.09.010.CrossRefGoogle Scholar
Graefe, Andreas. 2024. “The PollyVote Forecast for the 2024 US Presidential Election.” PS: Political Science & Politics. https://doi.org/10.1017/S104909652400101X.CrossRefGoogle Scholar
Graefe, Andreas. 2025. “Replication Data for: Combining Forecasts for the 2025 German Federal Election: The PollyVote.” PS: Political Science & Politics. DOI: 10.7910/DVN/XJMT0Y.CrossRefGoogle Scholar
Groß, Marcus. 2021. “A Long-Short Term Event Memory State-Space Model for Multi-Party Elections.” Zenodo, August 23. https://doi.org/10.5281/zenodo.3697270.CrossRefGoogle Scholar
Jérôme, Bruno, Jérôme, Véronique, and Lewis-Beck, Michael S.. 2025. “A Political-Economy Forecast of the 2025 German Federal Elections: Merz Wins but the Grand Coalition is Back.” PS: Political Science & Politics. DOI: 10.1017/S1049096525000186.CrossRefGoogle Scholar
Lawrence, Michael, Goodwin, Paul, O’Connor, Marcus, and Önkal, Dilek. 2006. “Judgmental Forecasting: A Review of Progress over the Last 25 Years.” International Journal of Forecasting 22 (3): 493518. https://doi.org/10.1016/j.ijforecast.2006.03.007.CrossRefGoogle Scholar
Marcinkiewicz, Kamil, and Stegmaier, Mary. 2025. “Predicting Support for the Christian Democrats in the 2025 German Bundestag Election: A State-Level Approach.” PS: Political Science & Politics. DOI: 10.1017/S1049096525000125.CrossRefGoogle Scholar
Quinlan, Stephen, Schnaudt, Christian, and Lewis-Beck, Michael S.. 2025. “A Political History Forecast of Bloc Support in the 2025 German Federal Election.” PS: Political Science & Politics. DOI: 10.1017/S1049096525000204.CrossRefGoogle Scholar
Selb, Peter, Chen, Sina, Körtner, John, and Bosch, Philipp. 2023. “Bias and Variance in Multiparty Election Polls.” Public Opinion Quarterly 87 (4): 1025–37. https://doi.org/10.1093/poq/nfad046.CrossRefGoogle Scholar
Shirani-Mehr, Houshmand, Rothschild, David, Goel, Sharad, and Gelman, Andrew. 2018. “Disentangling Bias and Variance in Election Polls.” Journal of the American Statistical Association 113 (522): 607–14. https://doi.org/10.1080/01621459.2018.1448823.CrossRefGoogle Scholar
Supplementary material: Link

Graefe Dataset

Link