We observe that an increasing number of formal theorists and quantitative methodologists are engaging in a similar line of research: drawing insights from formal theory to inform empirical methodology. This represents a kind of reversal of the Empirical Implications of Theoretical Models (EITM) approach, which derives testable hypotheses from formal theory and evaluates them using innovative empirical designs.
In contrast, the Theoretical Implications of Empirical Models/Methods (TIEM) framework seeks to apply tools from formal theory—such as decision theory and game theory—to re-examine, critique, and improve empirical methodologies. While EITM emphasizes theory testing, TIEM aims to provide formal foundations for the empirical strategies used to study human behavior and society. Understandably, people may hold different views on what TIEM entails; here, I primarily adopt a methodological perspective.
Why is this important? Social science differs fundamentally from the natural sciences in one key aspect: our research subjects are human beings—agents who act actively and strategically. Unlike phenomena in fields such as macro-physics or chemistry, social patterns are generally probabilistic and shaped by rational responses and equilibrium adjustments. Given this, empirical designs that ignore these features and routinely apply causal inference methods risk producing misleading or misinformed conclusions.
TIEM acknowledges these concerns and offers potential solutions. From a philosophical or intellectual history perspective, it bears resemblance to the Frankfurt School, which should be understood within the broader context of the intellectual and practical goals of critical theory. Beyond this connection, as an emerging field, I am optimistic about the development of a more unified framework—one that provides systematic tools and methods to better study social science.
This site aims to provide up-to-date resources and developments related to TIEM research. I am grateful for and welcome everyone’s help—if you know of any research or resources that are not listed here, please let me know. Thank you in advance!
De Mesquita, Ethan Bueno, and Scott A. Tyson. “The commensurability problem: Conceptual difficulties in estimating the effect of behavior on behavior.” American Political Science Review 114, no. 2 (2020): 375-391.[pre-print]
Fudenberg, Drew, and David K. Levine. “Learning in games and the interpretation of natural experiments.” American Economic Journal: Microeconomics 14, no. 3 (2022): 353-377.
Slough, Tara. “Phantom counterfactuals.” American Journal of Political Science 67, no. 1 (2023): 137-153.[pre-print]
Ashworth, Scott, Christopher R. Berry, and Ethan Bueno de Mesquita. “Modeling theories of women’s underrepresentation in elections.” American Journal of Political Science 68, no. 1 (2024): 289-303. [pre-print]
Besley, Timothy, and Anne Case. “Unnatural experiments? Estimating the incidence of endogenous policies.” The Economic Journal 110, no. 467 (2000): 672-694.[pre-print]
Slough, Tara, and Scott A. Tyson. “External Validity and Meta‐Analysis.” American Journal of Political Science 67, no. 2 (2023): 440-455. [pre-print]
Slough, Tara, and Scott A. Tyson. “Sign-congruence, external validity, and replication.” Political Analysis (2022): 1-16. [pre-print]
Izzo, Federica, Torun Dewan, and Stephane Wolton. “Cumulative knowledge in the social sciences: The case of improving voters’ information.” Available at SSRN 3239047 (2018).
Slough, Tara, and Scott A. Tyson. External Validity and Evidence Accumulation. Cambridge University Press, 2024.
Fu, Jiawei, and Tara Slough. “Heterogeneous Treatment Effects and Causal Mechanisms.” arXiv preprint arXiv:2404.01566 (2024).
Ghanem, Dalia, Pedro HC Sant’Anna, and Kaspar Wüthrich. “Selection and parallel trends.” arXiv preprint arXiv:2203.09001 (2022).
Marx, Philip, Elie Tamer, and Xun Tang. “Parallel trends and dynamic choices.” Journal of Political Economy Microeconomics 2, no. 1 (2024): 129-171.[pre-print]
Eggers, Andrew C., Ronny Freier, Veronica Grembi, and Tommaso Nannicini. “Regression discontinuity designs based on population thresholds: Pitfalls and solutions.”American Journal of Political Science 62, no. 1 (2018): 210-229.[pre-print]
Eggers, Andrew C. “Quality-based explanations of incumbency effects.” The Journal of Politics 79, no. 4 (2017): 1315-1328.[pre-print]
Abramson, Scott F., Korhan Koçak, and Asya Magazinnik. “What do we learn about voter preferences from conjoint experiments?.” American Journal of Political Science 66, no. 4 (2022): 1008-1020.[pre-print]
Fu, Jiawei, and Xiaojun Li. “Generalization Issues in Conjoint Experiment: Attention and Salience.” arXiv preprint arXiv:2405.06779 (2024).
Eggers, Andrew C., Guadalupe Tuñón, and Allan Dafoe. “Placebo tests for causal inference.” American Journal of Political Science 68, no. 3 (2024): 1106-1121. [pre-print]
Stepane Wolton’s understanding of TIEM：https://stephanewolton.com/about/tiem/
Scott A. Tyson’s syllabus: https://www.sas.rochester.edu/psc/syllabi/20202021/508_TIEM_Syll.pdf