Lukas F. Stoetzer

I am a Professor of Quantitative Methods at the Department of Philosophy, Politics and Economics at the University of Witten/Herdecke.

Before I worked at the Humboldt University of Berlin, at the excellence cluster SCRIPTS, at the Department of Political Science at University of Zurich, and as a Postdoctoral Fellow at the Massachusetts Institute of Technology, Department of Political Science, on a project that was funded by the Fritz-Thyssen Foundation. I graduated from University of Mannheim at the Graduate School of Economic & Social Sciences in May 2015.

My research in quantitative methods focuses on the application of causal inference and measurement methods. My substantive research agenda pertains to understanding political behaviour and its consequences in representative democracies — spanning voting decisions, party competition, coalition politics, and the challenge posed by populism and the radical right. To find answers to the question how voters’ attitudes and behaviour influence democratic quality and representation, I develop quantitative research methods, forecast elections, and build on formal theoretical decision making processes.

news

May 21, 2026	Publication in Political Analysis
Dec 1, 2025	Two Publications in the Journal of Politics
Jun 16, 2024	Publication in the American Journal of Political Science

selected publications

How parties react to voter transitions

Tarik Abou-Chadi, and Lukas F Stoetzer

American Political Science Review 2020

Party Competition

Abs Bib Code Website Scholar

This letter investigates how voter transitions between parties affect parties’ policy positioning. While a growing literature investigates the role of election results as signals for parties’ policy adaption, it has mostly focused on vote changes of individual parties. However, parties do not know only whether they have won or lost in an election; they also have detailed information on which parties they won votes from and which parties they lost votes to. We make two arguments about how voter transitions should affect the strategic policy choices of political parties. First, when a party has lost votes to another party it will adapt its policy positions toward that party. Second, parties that have overall lost more votes become more likely to adapt their positions. Making use of a data set on individual voter transitions and party positions we can demonstrate that voter transitions indeed affect parties’ competitive behavior.
@article{abou2020parties, bibtex_show = {true}, status = {published}, preview = {apsr.jpg}, impact = {1}, website = {https://doi.org/10.1017/S0003055420000155}, title = {How parties react to voter transitions}, keywords = {Party Competition}, author = {Abou-Chadi, Tarik and Stoetzer, Lukas F}, journal = {American Political Science Review}, volume = {114}, number = {3}, pages = {940--945}, year = {2020}, publisher = {Cambridge University Press}, selected = {true}, code = {https://doi.org/10.7910/DVN/HULLNG} }
Causal Inference with Latent Outcomes

Lukas F Stoetzer, Xiang Zhou, and Marco Steenbergen

American Journal of Political Science 2025

Methods

Abs Code Website Scholar

While causal inference has become front and center in empirical political science, we know little about how to analyze causality with latent outcomes, such as political values, beliefs, and attitudes. In this article, we develop a framework for deﬁning, identifying, and estimating the causal effect of an observed treatment on a latent outcome, which we call the latent treatment effect (LTE). We describe a set of assumptions that allow us to identify the LTE and propose a hierarchical item response model to estimate it. We highlight an often overlooked exclusion restriction assumption, which states that treatment status should not affect the observed indicators other than through the latent outcome. A simulation study shows that the hierarchical approach offers unbiased estimates of the LTE under the identiﬁcation and modeling assumptions, whereas conventional two-step approaches are biased. We illustrate our proposed methodology using data from two published experimental studies
Coalition-directed Voting under Uncertainty

Oke Bahnsen, Lukas F Stoetzer, and Thomas Gschwend

Journal of Politics 2025

Coalition PoliticsVoting Decisions

Abs Bib Code Website Scholar

When voters support parties in multi-party democracies, it is often uncertain what coalition government the party will join. How do voters deal with the lack of clarity in parties’ coalition government prospects? We develop a novel conceptualization of coalition-directed voting to study the effects of this type of uncertainty. We present observational and experimental evidence that supports the idea that voters are risk-averse when considering coalition government options. Observational survey analyses show that the perception of uncertain coalition prospects negatively affects the propensity to vote for such a party, even when holding the expected coalition government payoffs constant. Using a survey vignette experiment, we provide causal evidence that uncertain coalition prospects reduce the propensity to support a party, compared to certain coalition prospects given the same expected coalition government payoffs. Together, these findings provide insights for our understanding of party competition and parties’ coalition strategies.
@article{bahnsen2022, bibtex_show = {true}, status = {published}, year = {2025}, title = {Coalition-directed Voting under Uncertainty}, code = {https://doi.org/10.7910/DVN/HL64WC}, keywords = {Coalition Politics, Voting Decisions}, project = {pec}, impact = {1}, author = {Bahnsen, Oke and Stoetzer, Lukas F and Gschwend, Thomas}, journal = {Journal of Politics}, preview = {jop2.png}, volume = {First View}, selected = {true}, website = {https://doi.org/10.1086/736445} }
Estimating Treatment Effects on Proportions with Synthetic Controls

Konstantin Bogatyrev, and Lukas F. Stoetzer

Political Analysis 2026

Methods

Abs Bib Code Website Scholar

Synthetic control methods are widely used for causal inference in case studies and panel data settings, often applied to model counterfactuals for proportional outcomes. However, conventional synthetic control methods are designed for univariate outcomes, leading researchers to model counterfactuals for each proportion separately. We make the case for jointly estimating synthetic controls across multiple compositional outcomes. Using the same weights for each proportion establishes a constant control comparison, improving comparability while adhering to important treatment constraints. We illustrate the benefits of the method through a simulation and two applications to recent empirical studies. This implementation integrates naturally with a wide range of synthetic control approaches, providing interpretable estimates for compositional panel data common in political science.
@article{bogatyrev2024, bibtex_show = {true}, status = {published}, title = {Estimating Treatment Effects on Proportions with Synthetic Controls}, code = {https://doi.org/10.7910/DVN/MPUEIC}, keywords = {Methods}, author = {Bogatyrev, Konstantin and Stoetzer, Lukas F.}, year = {2026}, journal = {Political Analysis}, volume = {First View}, pages = {1--17}, impact = {1}, doi = {10.1017/pan.2026.10046}, website = {https://doi.org/10.1017/pan.2026.10046}, publisher = {Cambridge University Press}, selected = {true}, preview = {pa.jpg} }