REGISTER HERE

Abstract: Two-way fixed effects (TWFE) models are the most commonly used method in panel analyses to draw causal conclusions. However, recent methodological developments have cast doubt on TWFE models from several angles: (1) they lack a clear design or exposition of the treatment assignment mechanism; (2) their identification assumptions are often violated; and (3) their rigid functional form causes a weighting problem, which makes the estimated coefficient uninterpretable. This talk will elaborate on these issues and provide potential remedies for applied researchers.

Bio: Yiqing Xu is an Assistant Professor at the Department of Political Science at Stanford University. His primary research covers political methodology, Chinese politics, and their intersection. He received a PhD in Political Science from Massachusetts Institute of Technology in 2016. His work has appeared in American Political Science Review, American Journal of Political Science, Journal of Politics, and Political Analysis, among other peer-reviewed journals. He has won several professional awards, including the best article award from the American Journal of Political Science in 2016 and the Miller Prize (2018, 2020) for the best work appearing in Political Analysis the preceding year.

Learn more about Prof. Yiqing Xu at his website.