Thomas Leavitt
Asst Professor
Marxe School of Public and International Affairs
Department: Public Affairs
Areas of expertise:
Email Address: thomas.leavitt@baruch.cuny.edu
> View CV- Biography
- Teaching
- Research and Creative Activity
- Grants
- Honors and Awards
- Service
Thomas Leavitt is an Assistant Professor at the Marxe School of Public and International Affairs, Baruch College, City University of New York, and an affiliate of the CUNY Institute for Demographic Research. He is also an Evaluation and Evidence Consulting Fellow with the Arnold Ventures Criminal Justice Evaluation Network.
He develops statistical methods for causal inference, especially sensitivity analysis for observational studies and Bayesian causal inference with randomization-based guarantees. Much of that work is motivated by questions of race in politics and public policy, which raise inferential problems that standard tools handle poorly. His research appears in the Annals of Applied Statistics, International Statistical Review, the Journal of Causal Inference, Observational Studies, Political Analysis, and Political Science Research and Methods.
He earned his Ph.D. in Political Science, specializing in methodology, from Columbia University in 2021. From 2021 to 2023 he was a Postdoctoral Research Fellow at Harvard University, where he worked on difference-in-differences and related methods for evaluating public policy.
Education
Ph.D., Political Science, Columbia University New York United States
M.Phil., Political Science, Columbia University New York United States
M.A., Political Science, Columbia University New York United States
M.A., Committee on International Relations, University of Chicago Chicago United States
B.A., Political Science, DePauw University Greencastle United States
Journal Articles
(2026). Which Effect of Race? Causal Inference without Holding All Else Equal. American Political Science Review (Under Review),
(2026). Beyond Pretrends: A Discordance-Based Sensitivity Analysis for Difference-in-Differences. Observational Studies (Accepted),
(2026). Navigating the Mismeasurement of Intermediary Variables in Message-Based Experiments. Political Science Research and Methods (First View),
(2026). Building a Design-Based Matching Pipeline: From Principles to Practical Implementation in R. Observational Studies (Accepted),
(2026). Fisher Meets Bayes: The Value of Randomisation for Bayesian Inference of Causal Effects. International Statistical Review, 94(1). 188–201.
(2026). Sequential Sensitivity Analysis for Multiple Assumptions: A Framework for Understanding Racial Disparity in Police Use of Force. Journal of the American Statistical Association (Revise and Resubmit),
(2025). Averaged Prediction Models (APM): Identifying Causal Effects in Controlled Pre-Post Settings with Application to Gun Policy. Annals of Applied Statistics, 19(3). 1826–1846.
(2024). Audit Experiments of Racial Discrimination and the Importance of Symmetry in Exposure to Cues. Political Analysis, 32(4). 445–462.
(2023). Randomization-based, Bayesian Inference of Causal Effects. Journal of Causal Inference, 11(1). Article 20220025.
Book Chapters
(2023). Challenges that Proprietary Research Poses for Meta-Analysis. The Oxford Handbook of Engaged Methodological Pluralism in Political Science (p. 257–271). Oxford University Press.
Bowers, J., & Leavitt, T. (2020). Causality and Design-Based Inference. The SAGE Handbook of Research Methods in Political Science and International Relations (p. 769–804). SAGE Publications.
Presentations
Leavitt, T. (2026, November 15). Randomization-Based Bayesian Inference of Causal Effects: Guarantees, Calibration, and the Connection to Theory. SLDS 2026 Conference on Statistical Learning and Data Science, Invited Session: Robust Causal Inference Under Real-World Complications. : American Statistical Association Section on Statistical Learning and Data Science.
Leavitt, T. (2026, October 15). Joint Sensitivity Analysis for Multiple Assumptions. Data Science Frontiers: Society and Politics. : NYU Abu Dhabi Institute in New York, New York University Abu Dhabi.
Leavitt, T. (2026, November 15). Joint Sensitivity Analysis for Multiple Assumptions: Unpacking Racial Disparity in Police Use of Force. Methods Workshop. : Department of Political Science, Vanderbilt University.
Leavitt, T. (2026, January 15). Joint Sensitivity Analysis for Multiple Assumptions: Unpacking Racial Disparity in Police Use of Force. Statistics Winter Workshop: Causal Inference and its Applications. : Departments of Statistics and Economics, University of Florida.
Leavitt, T. (2026, April 15). Audit Experiments of Racial Discrimination and the Importance of Symmetry in Exposure to Cues. Data Science Cluster Meeting. : Baruch College, City University of New York.
Leavitt, T. (2026, February 15). Audit Experiments of Racial Discrimination and the Importance of Symmetry in Exposure to Cues. Political Methodology Colloquium. : Department of Political Science, Columbia University.
Leavitt, T. (2026, October 15). Audit Experiments of Racial Discrimination and the Importance of Symmetry in Exposure to Cues. Political Science 5016: Field Experiments in Political Science (guest lecture). : Department of Political Science, Washington University in St. Louis.
Leavitt, T. (2026, August 15). Model Selection for Reducing Sensitivity to Unobserved Confounding in Controlled Pre-Post Designs. Joint Statistical Meetings, Invited Paper Session: Planning Observational Studies with Unobserved Confounding in Mind. : American Statistical Association.
Leavitt, T. (2026, March 15). Parsing Taste-Based from Statistical Discrimination in Audit Experiments. Data Science Lunch Seminar Series. : The Center for Data Science, New York University.
Leavitt, T. (2026, October 15). Model Selection for Decreasing Dependence on Counterfactual Identification Assumptions in Controlled Pre-Post Designs. Quantitative Methods Workshop. : Wilf Family Department of Politics, New York University.
Leavitt, T. (2026, October 15). Model Selection for Decreasing Dependence on Counterfactual Identification Assumptions in Controlled Pre-Post Designs. Applied Statistics Workshop. : The Institute for Quantitative Social Science, Harvard University.
Leavitt, T., Bowers, J., & Miratrix, L. W. (2026, December 15). Sensitivity analysis for null results: Implications for studies of racially biased policing. 15th International Conference of the ERCIM Working Group on Computational and Methodological Statistics (CMStatistics 2022). : ERCIM Working Group on Computational and Methodological Statistics (CMStatistics), King’s College London.
Leavitt, T., & Green, D. P. (2026, September 15). The Challenge of Meta-Analysis in Domains Where Many (Most?) Studies are Proprietary: Bayesian Updating under Selective Reporting. Pre-APSA Workshop: "Knowledge Accumulation and External Validity: Implications for Design and Analysis.". : Evidence in Governance and Politics (EGAP) and Centre for the Study of Democratic Citizenship (CSDC), McGill University.
Leavitt, T. (2026, March 15). Potential Outcome & Directed Acyclic Graphs (DAGs). The Miratrix C.A.R.E.S. Lab. : Graduate School of Education and Department of Statistics, Harvard University.
Leavitt, T. (2026, January 15). Major debates in African politics: Colonial rule, anti-colonial resistance and postindependence colonial legacies. B8772-001 — Global Immersion in East Africa. : Columbia Business School and Chazen Institute for Global Business, Columbia University.
Leavitt, T. (2026, April 15). Randomization-based, Bayesian Inference of Causal Effects. Quantitative Methods Workshop. : Wilf Family Department of Politics, New York University.
Other Scholarly Works
Leavitt, T., Hatfield, L., & Greifer, N. (2025). apm: Averaged Prediction Models. R package version 0.1.1.
Zeldow, B., Leavitt, T., & Hatfield, L. (2023). Difference-in-Differences (website).
College
| Committee Name | Position Role | Start Date | End Date |
|---|---|---|---|
| Peer Teaching Observations of Marxe Faculty Colleagues | Observer | Present | |
| Higher Education Administration and MPA Program Learning Assessment | Assessor | 5/31/2026 | |
| Learning Assessment Committee | Committee Member | 8/31/2025 |