Robust IV Inference with Clustering Dependence (Job Market Paper)
Presented at 2020 European Winter Meeting of the Econometric Society
Estimation and Inference for Synthetic Control Methods with Spillover Effects
with Connor Dowd, Feb 2019. [Matlab, R]
Presented at 2019 North America Summer Meeting of the Econometric Society, and 2019 China Meeting of the Econometric Society
Inference for Dependent Data with Cluster Learning (draft coming soon)
with Christian Hansen, Damian Kozbur, and Lucciano Villacorta, Nov 2020. [abstract]
Presented at 2020 World Congress of the Econometric Society, 2020 North American Winter Meeting of the Econometric Society, 2019 European Winter Meeting of the Econometric Society, and 2019 Midwest Econometrics Group
Abstract: This paper presents and analyzes an approach to inference for dependent data. The primary setting considered here is with spatially indexed data in which the dependence structure of observed random variables is characterized by an observed dissimilarity measure over spatial indeces. Observations are partitioned into clusters with the use of an unsupervised clustering algorithm applied to the dissimilarity measure. Once the partition into clusters is learned, a cluster-based inference procedure is applied to a statistical hypothesis test. The procedure proposed in the paper allows the number of clusters to depend on the data, which gives researchers a principled method for choosing an appropriate clustering level. The paper gives conditions under which the proposed procedure asymptotically attains correct size.
On the Empirical Content of the Beckerian Marriage Model
with 67(2), 349–362.
Principal Component and Static Factor Analysis
with Chris Gu and Yike Wang, in Macroeconomic Forecasting in the Era of Big Data ed. by Peter Fuleky, 2020, 229-266. Advanced Studies in Theoretical and Applied Econometrics, vol 52, Springer, Cham.
Work in Progress
Optimal Inference under Weak Identification
with Tetsuya Kaji. This project studies the optimality of inference methods in the general formulation of weak identification in semiparametric models, i.e., when a parameter is weakly regular. Under weak identification, standard methods usually fail to deliver valid inference. We formulate a class of inference procedures that are robust to weak identification. We show that by considering the quotient space of the underlying regular parameter space, the efficiency results of van der Vaart (1991) can be extended to our case.