Economics

We present a systematic method for pruning edges from causal graphs by leveraging tiered knowledge. We characterize conditions under which edges can be removed from a causal graph while preserving the identifiability of (conditional) causal effects. This result enables causal identification on simplified graphs that are substantially smaller than the original graphs. The approach is particularly valuable

Large language models (LLMs) are increasingly deployed in real-world applications such as chatbots, writing assistants, and text summarization tools. As these applications become more central to user-facing tasks, robust evaluation of their performance becomes critical, not only for ensuring quality but also for guiding continuous improvement. Traditional evaluation approaches rely on intrinsic metrics

Causal discovery is central to enable causal models for tasks such as effect estimation, counterfactual reasoning, and root cause attribution. Yet existing approaches face trade-offs: purely statistical methods (e.g., PC, LiNGAM) often return structures that overlook domain knowledge, while expert-designed DAGs are difficult to scale and time-consuming to construct. We propose CausalFusion, a hybrid framework

Switchback experiments assign units to treatment and control over time, yielding more precise causal estimates than fixed designs but risking bias from carryover effects, where past treatments influence future outcomes. Existing estimators require specifying an influence period, i.e. an upper bound on carryover duration, often guessed from intuition. We propose a statistical test that detects when this

In A/B testing, statistical power depends on both the variance of estimated impacts and the distribution of true impacts. A low variance metric can have low power if true impacts on the metric tend to be small, while a high variance metric can have high power if true impacts on the metric tend to be large. Traditional power calculations, however, focus solely on the variance of estimated impacts. They compute