The Gosnell Prize

The Gosnell Prize for Excellence in Political Methodology is awarded for the best work in political methodology presented at any political science conference during the preceding year.

2024 Winner
Recipient
Jiawei Fu and Tara Slough
Work Heterogeneous Treatment Effects and Causal Mechanisms
Citation

Fu and Slough re-examine one of the most common empirical practices in political science---estimating heterogeneous treatment effects (HTE) as a test of causal mechanisms. Despite the popularity of HTE analyses, how HTEs connect to causal mechanisms is often only discussed with intuitions without a formal framework. By explicitly connecting the mediation framework and HTE analyses, Fu and Slough develop a framework to understand when the existence of HTEs can support inferences about the activation of a mechanism. They demonstrate that interpreting HTEs as evidence for mechanisms requires what they call the exclusion assumption---the moderator of interest introduces heterogeneity only with respect to indirect effects specific to the mechanism of interest and does not introduce heterogeneity with respect to other mechanisms. As the authors articulate, the logic is straightforward, but it remains implicit in most uses of heterogeneous treatment effects to detect mechanisms. They also clarify that there is no logical ordering between this exclusion assumption and the sequential ignorability assumption necessary for mediation analysis, implying that HTE analyses are neither more nor less agnostic tests of mechanisms than mediation analysis. Fu and Slough's paper will help a wide range of applied scholars understand how to properly interpret HTEs as a mechanism test, and we also expect that their paper will inspire additional methodological developments about HTE analyses, mechanisms, and causal inference. This paper is also a great example of recent developments in theoretical implications of empirical models (TIEM). We congratulate the authors on this excellent contribution to political methodology.

Selection committee Bryce Dietrich (Purdue), Dorothy Kronick (Berkeley), Naoki Egami (Columbia), and Anand Sokhey (Colorado, chair)

 

 

Past Recipients

2022 Winner
Recipient
Joseph T. Ornstein (Georgia)
Elise N. Blasingame (Georgia)
Jake S. Truscott (Purdue)
Work "How to Train Your Stochastic Parrot: Large Language Models for Political Texts"
Citation Ornstein, Blasingame, and Truscott propose a new simple approach to using the recent large language models for political texts. Using the pre-registered analyses, the authors showed that, by tailoring prompts, a simple prediction from the GPT-3 can outperform conventional supervised learning methods in various text-as-data tasks in political science (e.g., sentiment analysis, ideological scaling, and topic modeling). We were impressed by the performance of the proposed approach, as well as the authors’ careful and modest validation through pre-registration of a range of tasks. The award committee thinks that this paper can help political scientists and political methodologists generate a series of new ideas about how political scientists can apply and modify the large language model (like GPT-3 and GPT-4) for our own tasks, and, importantly, how we validate their performance in each application carefully. There are a large number of open questions, like how best to engineer prompts, how best to fine-tune predictions for political texts using domain knowledge, and how best to apply (or not to apply) these methods to corpora outside of the pre-training data. Ornstein et al.’s work will be a great starting point for further methodological developments. We congratulate the authors on this fine contribution to work on natural language processing and text-as-data methods in political science.
Selection committee Bryce Dietrich (Purdue), Dorothy Kronick (Berkeley), Naoki Egami (Columbia), and Anand Sokhey (Colorado, chair)

2021 Winner Recipient

Avidit Acharya (Stanford)
Kirk Bansak (UC San Diego)
Jens Hainmueller (Stanford)

Work "Combining Outcome-Based and Preference-Based Matching: A Constrained Priority Mechanism" Citation Acharya et al.'s paper opens up a new opportunity to connect political methodology, machine learning, and mechanism design — the latter is a lively field in Economics, and has clear implications for designing real-world institutions. This paper tackles one of the most important problems in society and in political science — refugee settlements and integration — by designing a mechanism to allocate refugees while taking into account the preferences of both refugees and planners. Moreover, the paper is notable in that it provides three significant contributions: (1) it connects two large literatures that have been studied separately, (2) it provides a new methodological/theoretical contribution, and (3) it provides an important application (the authors are implementing it with the Dutch government). Selection committee Skyler Cranmer (Ohio State), Naoki Egami (Princeton), and Anand Sokhey (Colorado, chair)

Year Recipient Work
2020 Dean Knox (Princeton), Christopher Lucas (Wash U) "A Dynamic Model of Speech for the Social Sciences"
2019 Naoki Egami (Princeton) "Identification of Causal Diffusion Effects using Stationary Causal Directed Acyclic Graphs"
2018 Fredrik Savje (Yale), Peter Aronow (Yale), and Michael Hudgens (UNC) "A Folk Theorem on Interference in Experiments"
2017 Matthew Blackwell (Harvard) "Instrumental Variable Methods for Conditional Effects and Causal Interaction in Voter Mobilization Experiments"
2016 Marc Rotkovic (Princeton), Dustin Tingley (Harvard) "Sparse Estimation with Uncertainty: Subgroup Analysis in Large Dimensional Designs"
2015 Sebastian Calonico, Matias Cattaneo, and Rocio Titiunik "Robust Nonparametric Confidence Intervals for Regression-Discontinuity Designs"
2014 Margaret E. Roberts (UC San Diego), Brandon M. Stewart (Harvard), Dustin Tingley (Harvard), Christopher Lucas (Harvard), Jetson Leder-Luis (Caltech), Shana Gadarian (Syracuse), Bethany Albertson (UT Austin), and David Rand (Yale) "Topic Models for Open-Ended Survey Responses with Applications to Experiments"
2013 Adam Glynn and Konstantin Kashin (Harvard) "Front-door Versus Back-door Adjustment with Unmeasured Confounding: Bias Formulas for Front-door and Hybrid Adjustments."
2012 Thomas Gschwend, James Lo, and Sven-Oliver Proksch (University of Mannheim) "A Common Left-Right Scale for Voters and Parties in Europe."
2011 Robert J. Franzese, Jr. (University of Michigan), Jude C. Hays, Aya Kachi (University of Illinois) "Modeling History-Dependent Network Coevolution"
2010 Jong Hee Park (University of Chicago) "Joint Modeling of Dynamic and Cross-Sectional Heterogeneity: Introducing Hidden Markov Panel Models"
2009 John Freeman (University of Minnesota), and Jeff Gill (Washington University in St. Louis) "Dynamic Elicited Priors for Updating Covert Networks."
2008 Kevin Quinn (Harvard) "What Can be Learned from a Simple Table? Bayesian Inference and Sensitivity Analysis for Causal Effects from 2x2 and 2x2xK Tables in the Presence of Unmeasured Confounding."
2007 Alberto Abadie, Alexis Diamond, and Jens Hainmueller (Harvard) "Estimating the Effect of California's Tobacco Control Program."
2006 Michael Penn Colaresi (Michigan State), Michael Crespin (University of Georgia), Burt L. Monroe (Michigan State), Kevin M. Quinn (Harvard), and Dragomir R. Radev (University of Michigan) "An Automated Method of Topic-Coding Legislative Speech Over Time With Application to the 105th-108th U.S. Senate"
2005 Alexis Diamond (Harvard) and Jasjeet S. Sekhon (UC Berkeley) "Genetic Matching for Estimating Causal Effects: A General Multivariate Matching Method for Achieving Balance in Observational Studies."
2004 Henry Brady, John McNulty (UC Berkeley) "A “Natural Experiment” on the Costs of Voting: Methodologies for Analyzing Observational Data when the Treatment is Nearly Randomized."
2003 Won-Ho Park (University of Michigan) "Estimation of Voter Transition Rates and Ecological Inference."
2002 Janet Box-Steffensmeier (Ohio State), and Suzanna De Boef (Penn State) "A Monte Carlo Analysis for Recurrent Events Data."
2001 Andrew D. Martin, Kevin M. Quinn (University of Washington) "Bayesian Learning about Ideal Points of U.S. Supreme Court Justices, 1953-1999."
2000 Curtis S. Signorino, Kuzey Yilmaz (University of Rochester) "Strategic Misspecification in Discrete Choice Models."
1999 Nathaniel Beck (UC San Diego), Gary King (Harvard), and Langche Zeng (Harvard University on leave from GWU) "Improving Quantitative Studies of International Conflict: A Conjecture."
1998 Dean Lacy (Ohio State) "A Theory of Nonseparable Preferences in Survey Responses."
1997 Gary King (Harvard) "A Solution to the Ecological Inference Problem: Reconstructing Individual Behavior From Aggregate Data."
1996 Nathaniel Beck (UC San Diego), and Richard Tucker (Indiana) "Conflict in Space and Time: Time-Series-Cross-Section Analysis with a Binary Dependent Variable."
1996 Walter R Mebane, Jr., and Jonathan Wand (Cornell University) "Markov Chain Models for Rolling Cross-section Data: How Campaign Events and Political Awareness Affect Vote Intentions and Partisanship in the United States and Canada."
1995 Janet M. Box-Steffensmeier (Ohio State), Renee Smith (University of Rochester) "The Microfoundations of Aggregate Partisanship."
1995 Bradley Palmquist (Harvard) "Respecification Approaches to Ecological Inference: A Comparison of Control Variables and the Quadratic Model."

Past Selection Committees

Year Committee
2020 Anand Sokhey (Colorado, chair), Naoki Egami (Princeton), and Skyler Cranmer (Ohio State)
2019 Matthew Blackwell (Harvard), Marc Ratkovic (Princeton), and Fredrik Savje (Yale)
2018 Matthew Blackwell (Chair), Marc Ratkovic, Fredrik Savje
2017 Michael Peress (Chair), Matt Blackwell, Marc Ratkovic
2016 Michael Peress (Chair), Suzanne Linn, Brandon Stewart
2015 Jake Bowers (Chair), Adam Glynn, Xun Pang
2014 Jake Bowers (Chair), Adam Glynn, Xun Pang
2013 Jay Goodliffe (Chair), Jong Hee Park, Michael Peress
2012 Jay Goodliffe (Chair), Jong Hee Park, Michael Peress
2011 Matthew Lebo (Chair), Kenneth Kollman, Betsy Sinclair
2010 Matthew Lebo (Chair), Kenneth Kollman, Betsy Sinclair
2009 Kenneth Kollman (Chair), Betsy Sinclair, Matthew Lebo
2008 Kenneth Kollman (Chair)
2007 Michael Ward (Chair), Michael Crespin (winner from previous year), Patrick Brandt
2006 Michael Ward (Chair), Alexis Diamond (winner from previous year), Robert Luskin