Estimating a Counter-Factual with Uncertainty Through Gaussian Process Projection

February 26, 2021

GLODEM AI & CSS Seminar Series

GLODEM proudly presents the debut of its Spring 2021 AI & CSS Seminar Series with David Carlson & Devin Brown’s talk on March 5th (Friday), which will be co-hosted by the Department of International Relations.

GLODEM AI & CSS Seminar Series brings together practitioners working on AI usage in various fields and scholars specializing in computational social sciences. The seminar series is moderated by MA-CSSL, which is an interdisciplinary research laboratory at Koç University, established with the purpose of conducting cutting-edge research on the applications of computational methods to social science questions.

Date: 5 March 2021 – Friday

Time: 18:00- 19:30

Speakers: Dr. David Carlson, Assistant Professor of International Relations at Koç University & Devin P. Brown, MA Student of Political Science & International Relations at Koç University

Title: Estimating a Counter-Factual with Uncertainty Through Gaussian Process Projection

Abstract: Estimating a counter-factual in which a treatment did not occur allows political science researchers to better understand the effect of an intervention. To date, the most prominent attempt in the literature has been the introduction of the synthetic control method. However, this method has important and related drawbacks. Perhaps most importantly, the synthetic control method does not lend well to estimates of uncertainty, making traditional hypothesis testing ad hoc. We develop a new method, Gaussian process projection (GPP), that circumvents the issues associated with the synthetic control method. By comparing the projected unit to the true unit, we can estimate the causal effect of an intervention, and by using the measure of uncertainty, we can determine how unlikely the difference would be due to chance. After demonstrating the usefulness of the method in traditional settings, we generalize the method to allow for multiple treated units, treated at different times, and allow for link functions for applications with discrete outcomes.

Bio: David Carlson is an assistant professor in the Department of International Relations at Koç University. His research predominantly involves political methodology, with an interest in comparative politics and international political economy. Before coming to İstanbul, he received his PhD from the Department of Political Science at Washington University in St. Louis, under the advisement of Jacob M. Montgomery. His current projects involve the implementation of machine learning algorithms for prediction and inference in political science. He has published in American Political Science Review, Political Science Research and Methods, British Journal of Political Science, and Journal of Peace Research.

Devin P. Brown is a Master’s student at Koç University. His current research focuses on pro-government militias and civil conflict as well as quantitative methodology. He will be pursuing a PhD in the US beginning in Fall 2021.


Please visit to register for the event (advance registration required)