Abstract: In this talk, Dr. Ma will introduce a new local ReLU network least squares weighting method to estimate quantile dose-response functions. Unlike the conventional inverse propensity weighting (IPW) method, the weighting function involved in the treatment effect estimator will be estimated directly through local ReLU least squares optimization. The proposed method takes advantage of ReLU networks to alleviate the dimensionality problem of covariates and local kernel smoothing for the continuous treatment to precisely estimate the quantile dose-response function. The method enjoys computational convenience and scalability. It improves robustness and numerical stability compared to the conventional IPW method. For the ReLU network approximation, Dr. Ma will introduce a mixed fractional Sobolev class and show that the two-layer ReLU networks can break the “curse of dimensionality” when the weighting function belongs to this function class. She will establish the convergence rate for the ReLU network estimator and the asymptotic normality of the proposed estimator for the quantile dose-response function.
About the speaker: Dr. Shujie Ma is a Professor and Graduate Advisor in the Department of Statistics at the University of California, Riverside. Her research spans statistical methodology, theory, and computation, with a focus on modern data science challenges. She works on deep learning theory and applications, causal inference, clustering, time-series analysis, and network data analysis, with applications to biomedical and econometric studies. She has served on the editorial boards of several leading statistical journals, including the Annals of Statistics, Journal of the American Statistical Association, Journal of Business & Economic Statistics, and Journal of Computational and Graphical Statistics, among others. She is currently a Co-Editor of ASA Discoveries.
.png){kind=logo}
