🤖 AI Summary
Quantifying uncertainty in two-way fixed-effects estimation for networked data remains challenging due to violations of standard independence and homogeneity assumptions. To address this, we propose Branched Fixed Effects (BFE): a method that partitions the sample into statistically independent branches to enable unbiased causal inference and precise uncertainty quantification for treatment effects. BFE is the first to systematically integrate sample splitting into fixed-effects models under network dependence, thereby relaxing conventional assumptions—such as effect homogeneity or restrictive higher-order dependency structures—implicit in traditional standard error estimators. We develop an efficient, scalable algorithm supporting parallel branch extraction and estimation, enabling application to large-scale network data. Empirical evaluation on the Veneto firm-wage benchmark dataset (Italy) demonstrates that BFE substantially improves inferential robustness and interpretability. By ensuring replicability across research teams and facilitating transparent dissemination of credible estimates, BFE establishes a new paradigm for trustworthy causal inference in network settings.
📝 Abstract
Economists often rely on estimates of linear fixed effects models developed by other teams of researchers. Assessing the uncertainty in these estimates can be challenging. I propose a form of sample splitting for network data that breaks two-way fixed effects estimates into statistically independent branches, each of which provides an unbiased estimate of the parameters of interest. These branches facilitate uncertainty quantification, moment estimation, and shrinkage. Algorithms are developed for efficiently extracting branches from large datasets. I illustrate these techniques using a benchmark dataset from Veneto, Italy that has been widely used to study firm wage effects.