Graduate Student Posters (Emerging Cohort, Methods)

Estimating Heterogeneous Effect on Clustered Data Using Mixed-Effects Model

Junlong Zhou (New York University)

Abstract: Estimating the heterogeneous treatment effect is essential to assess the generality and mechanism of randomized experiments. In this paper, we propose an extension of the regression forest combining mixed-effects to analyze heterogeneous treatment effect using aggregated data sets. We show that including mixed-effects can improve estimation by accounting for the cluster-level...

Read more about Estimating Heterogeneous Effect on Clustered Data Using Mixed-Effects Model

Estimating Historical Election Results Under Counterfactual Electoral Systems

Samuel Baltz (University of Michigan)

Abstract: Despite the salience and importance of electoral system reform, both in the political science literature and in the contemporary politics of many democracies, little direct attention has been paid to the following question: how might the results of a specific election have been...

Read more about Estimating Historical Election Results Under Counterfactual Electoral Systems

Estimating Population Quantities From Multiple Data Sources Using the Structural Tensor Factorization

Soichiro Yamauchi (Harvard University)

Abstract: Estimating population quantities such as public opinions from survey data is a fundamental task in many social science studies. In political science, there is a growing interest in estimating public opinions at the level smaller than the entire nation, such as states (Lax and Phillips...

Read more about Estimating Population Quantities From Multiple Data Sources Using the Structural Tensor Factorization

Formalization of Political Analysis: Matrix of Possibles States and Strategies

Fernando Rocha Rosario (Universidad Nacional Autónoma de México)

Abstract: In this paper I expose a technique which formalizes the political analysis using modal logic and theory of rational choice. For represent the...

Read more about Formalization of Political Analysis: Matrix of Possibles States and Strategies

Gaussian Process Models for Causal Inference With Time-Series Cross-Sectional Data

Nuannuan Xiang and Kevin Quinn (University of Michigan)

*Award for Best Graduate Student Poster - Methods*

Abstract: In this paper, we develop a class of Gaussian Process models to estimate treatment effects with time-series cross-sectional data, in which a subset of units...

Read more about Gaussian Process Models for Causal Inference With Time-Series Cross-Sectional Data

Keyword Assisted Topic Models

Shusei Eshima (Harvard University), Tomoya Sasaki (Massachusetts Institute of Technology) and Kosuke Imai (Harvard University)

Abstract: For a long time, many social scientists have conducted content analysis by using their substantive knowledge and manually coding documents. In recent years, however, fully automated...

Read more about Keyword Assisted Topic Models

Leveraging Observational Outcomes to Improve the Generalization of Experimental Results

Melody Huang (University of California, Los Angeles), Erin Hartman (University of California, Los Angeles), Naoki Egami (Columbia University) and Luke Miratrix (Harvard University)

*Award for Best Graduate Student Poster - Methods*

Read more about Leveraging Observational Outcomes to Improve the Generalization of Experimental Results

Measuring Issue-Specific Preferences From Votes

Sooahn Shin (Harvard University)

Abstract: How can we measure issue-specific ideal points using roll-call votes? Ideal points have been widely used for measuring ideology, yet its nature of latent space makes it difficult to target a...

Read more about Measuring Issue-Specific Preferences From Votes

Modeling Time and Space Together

Ali Kagalwala (Texas A&M University), Andrea Junqueira (Texas A&M University), Guy D. Whitten (Texas A&M University), Laron K. Williams (University of Missouri) and Cameron Wimpy (Arkansas State University)

Read more about Modeling Time and Space Together

New Frontiers in Dynamic Pie Modeling

Andrea Junqueira (Texas A&M University), Ali Kagalwala (Texas A&M University), Andrew Philips (University of Colorado Boulder) and Guy Whitten (Texas A&M University)

Abstract: In this paper, we...

Read more about New Frontiers in Dynamic Pie Modeling

Paragraph-Citation Topic Models for Corpora With Citation Networks

ByungKoo Kim, Yuki Shiraito and Saki Kuzushima (University of Michigan)

Abstract: Social scientists often analyze a corpus with a citation network among its documents, such as the corpus of the U.S. Supreme Court decisions. Existing topic models for document networks assume that the topic of a citation is...

Read more about Paragraph-Citation Topic Models for Corpora With Citation Networks

Priming Bias Versus Post-Treatment Bias in Experimental Designs

Jacob Brown (Harvard University), Matthew Blackwell (Harvard University), Sophie Hill (Harvard University), Kosuke Imai (Harvard University) and Teppei Yamamoto (Massachusetts Institute of Technology)

Abstract:  It is now widely recognized that conditioning on variables affected by a treatment can induce post-treatment bias when estimating causal...

Read more about Priming Bias Versus Post-Treatment Bias in Experimental Designs

Quantifying Triggers With Event Coincidence Analysis: An Application to Mass Civilian Killings in Civil War, 1989-2017

Angela Chesler (University of Notre Dame)

Abstract: Scholars of international relations, comparative politics, and peace and conflict studies are often interested in questions concerning the triggers of extreme political outcomes such as war, coups, and genocide. In a causal chain, a trigger is an immediate cause that can be...

Read more about Quantifying Triggers With Event Coincidence Analysis: An Application to Mass Civilian Killings in Civil War, 1989-2017

Scaling the Youtube Media Environment Using Network and Text Data

Soubhik Barari (Harvard)

Abstract: In an era where many Internet news-seekers prefer to watch rather than read their news, YouTube plays an important role in mass political communication, but remains entirely unstudied by political...

Read more about Scaling the Youtube Media Environment Using Network and Text Data

Sensitivity Analysis for Outcome Tests

Elisha Cohen (Emory University)

Abstract: Outcome tests, a method that can be used for evaluating bias in selection making processes, are especially useful when using administrative datasets that contain only observations after the selection process has occurred. I show the outcome test lower bound derived by Knox, Lowe, and Mummolo (...

Read more about Sensitivity Analysis for Outcome Tests

Supervised Learning Election Forensics With Multi-Agent Simulated Training Data

Fabricio Vasselai (University of Michigan)

Abstract: The main advantage of using Supervised Machine Learning (SML) techniques to detect election fraud would be resorting to model-free or model-ensemble approaches, instead of usual...

Read more about Supervised Learning Election Forensics With Multi-Agent Simulated Training Data