Andrew Gelman

Andrew Gelman is the Higgins Professor of Statistics and Professor of Political Science at Columbia University, where he also serves as director of the Applied Statistics Center. His dual appointments reflect his interdisciplinary approach to research and teaching, bridging statistical methodology with political science applications.

Gelman earned his Ph.D. from Harvard University in 1990. His educational background established the foundation for his influential career that combines rigorous statistical methodology with substantive social science inquiry. He has maintained a strong presence in both academic communities throughout his career, contributing to the development of statistical methods while applying them to pressing questions in political science and public policy.

Gelman's research spans an exceptionally wide range of topics at the intersection of statistics and social science. His work addresses fundamental questions in voting behavior, electoral systems, and political representation, while simultaneously advancing methodological innovations in Bayesian statistics, multilevel modeling, and data visualization. He has made significant contributions to understanding why it is rational to vote, why campaign polls are variable despite predictable elections, and how redistricting affects democracy. His methodological work spans statistical inference challenges in diverse contexts from toxicology to medical imaging, from arsenic exposure in Bangladesh to radon levels in homes, and from police practices to social network analysis. His development of multilevel regression and poststratification (MRP) has become a standard technique in survey analysis and small-area estimation.

Analysis of Gelman's recent publications reveals a continued focus on foundational statistical methodology with applications across multiple domains. His work demonstrates consistent attention to practical implementation challenges in Bayesian computation, causal inference, and survey methodology. A strong theme throughout his recent work is addressing the replication crisis through improved statistical practice, with particular emphasis on model checking, transparent reporting of uncertainty, and the integration of Bayesian methods with machine learning approaches. His research increasingly focuses on the practical implementation challenges of advanced statistical methods in real-world settings.

• Outstanding Statistical Application award from the American Statistical Association
• Best article published in the American Political Science Review
• Council of Presidents of Statistical Societies award for outstanding contributions by a person under the age of forty

As director of Columbia's Applied Statistics Center, Gelman oversees a hub for interdisciplinary statistical research and collaboration. He has mentored numerous students and researchers through the Center's activities, fostering a community that applies advanced statistical methods to real-world problems across various domains. His teaching includes graduate courses in quantitative political research and applied regression methods, reflecting his commitment to training the next generation of researchers in robust statistical practice. Gelman has taught courses including Principles of Quantitative Political Research, Quantitative Political Research, and Quantitative Methods II: Applied Regression.

Gelman leads research teams focused on developing and applying advanced statistical methods to social science questions. His work often involves collaboration across disciplines, bringing statistical expertise to address substantive questions in political science, public health, and social policy. The Applied Statistics Center under his direction serves as a nexus for methodological innovation and application, connecting statisticians with domain experts to tackle complex data challenges while promoting best practices in statistical analysis and communication.