Inference for Group Interaction Experiments
A common experimental research design is one in which individuals are put into groups and then interact within the groups under different group-level treatment conditions. We present methods for design-based inference for such "group interaction" experiments. A key consideration is that group interaction implies potential interference, which yields dependencies that should be accounted for when making inferential claims. We show that when interference is present, standard cluster robust inference is super population consistent in accounting for such dependencies for inference on marginalized causal effects that account for interference. When interference is not present but groups are formed through individual random assignment, individual-level heteroskedasticity robust inference is consistent for inference on the usual average treatment effect. We consider extensions to experiments in which group composition is restricted and for inference on covariate-conditional effects.
Cyrus Samii is Professor in the Wilf Family Department of Politics of New York University. He writes and teaches on quantitative social science methodology, with an emphasis on causal inference. He is a prominent expert on the design of quantitative field research and social science randomized controlled trials. His applied research has focused on testing strategies to address governance challenges in contexts affected by war. He has carried out field studies in sites across Africa, Asia, and Latin America in collaboration with partners including the World Bank, United Nations, US Agency for International Development, UK Department for International Development, and Danish International Aid Agency, as well as government agencies, non-governmental organizations, and civil society organizations in the respective countries. From 2019-2023 he was Executive Director of the Evidence in Governance and Politics (EGAP) network. His work has appeared in peer-reviewed journals in political science, economics, and statistics. He received his PhD in political science from Columbia University, a master’s in international affairs from the Columbia University School of International and Public Affairs, and BA from Tufts University.