Political Rankings

1. Framework

My research offers a practical framework for ranking data analysis in political science.

• Atsusaka, Y., & Landsman, T. (under editor review). Practical framework for ranking data analysis in political science: Illustrations with ranked-choice voting.
• Atsusaka, Y., & Singh, S. (2026). Ranking data in political science.

This forthcoming work will provide step-by-step guidance on data preparation, estimands, diagnostic checks, visualization, and reporting.

2. Statistical methods

Ranking questions let respondents express relative priorities across candidates, policies, identities, and other political objects. Careful design is essential because random responses can distort the resulting quantities of interest. Ranking data can also support experimental and quasi-experimental research on electoral behavior, including how a candidate’s placement on a ranked ballot shapes voter choices.

• Atsusaka, Y., & Kim, S. Y. S. (2025). Addressing measurement errors in ranking questions for the social sciences. Political Analysis, 33(4), 339–360.
• Atsusaka, Y. (2025). Analyzing ballot order effects when voters rank candidates. Political Analysis, 33(1), 64–72.

The rankingQ R package provides tools for estimation and visualization.

3. Data sources

Reusable data are essential for cumulative research on political rankings.

• Atsusaka, Y., & Holbrook, J. (2026). A dataset of tabulated results from American ranked-choice voting elections. Scientific Data.
• Atsusaka, Y., & Singh, S. (2026). Ranking data in political science.

Collaborators

My work on political rankings has been developed with several collaborators. Please reach out if you are interested in collaborating in this exciting area of research.

• Jordan Holbrook (University of Houston)
• Naijia Liu (Independent Scholar)
• Seo-young Silvia Kim (Seoul National University)
• Shubhangi Singh (University of Houston)
• Theodore Landsman (Georgetown University)