Causal inference: remove confounding or bias through propensity score weighting, mediation analysis in longitudinal setting, instrumental variable method.
Machine learning: combine machine learning method with counterfactual modeling, representations learning, domain adaptation.
Zeng, S., Li, F., Hu, L., & Li, F. Propensity score weighting analysis for survival outcomes using pseudo-observations.(submitted) [code]
Zeng, S., Lange, E., Archie, E., Alberts, S., Campos, F., & Li, F. Causal mediation analysis for longitudinal mediators and survival outcomes.
Zeng, S., Assaad, S., Datta, S., Tao, C., Carin, L., & Li, F. (2020). Double robust representation learning for counterfactual reasoning. arXiv preprint:2010.07866. [code]
Chapfuwa, P., Assaad, S., Zeng, S., Pencina, M., Carin, L., & Henao, R. (2020). Survival analysis meets counterfactual inference. arXiv preprint arXiv:2006.07756.
Poulos, J., & Zeng, S. (2020). RNN-based counterfactual prediction, with an application to homestead policy and public schooling (minor revision).
Zeng, S., Li, F., Wang, R., & Li, F. (2020). Propensity score weighting for covariate adjustment in randomized clinical trials. Statistics in Medicine. [code]
Zeng, S., Rosenbaum, S., Archie, E., Alberts, S., & Li, F. (2020). Causal mediation analysis for sparse and irregular longitudinal data. Annals of Applied Statistics (Forthcoming). [code][poster]
Assaad, S., Zeng, S., Tao, C., Datta, S., Mehta, N., Henao, R., Li, F., & Carin, L. (2020). Counterfactual representation learning with balancing weights. AISTATS 2021 (Forthcoming).
Zeng, S., Murat, B., Joel, P., Charles, D.,& Emre, K. (2020). Causal transfer random forest: leveraging observational and randomization studies. ACM Web Search and Data Mining, Oral Presentation. [slides][code]
Rosenbaum, S., Zeng, S., Campos, F. A., Gesquiere, L. R., Altmann, J., Alberts, S. C., ... & Archie, E. A. (2020). Social bonds do not mediate the relationship between early adversity and adult glucocorticoids in wild baboons. Proceedings of the National Academy of Sciences, 117(33), 20052-20062. [code]
Zeng, S., Li, F., & Ding, P. (2020). Is being the only child harmful to psychological health?: Evidence from an instrumental variable analysis of China's One-Child Policy. Journal of Royal Statistical Society, Series A, 183(4), 1615-1635. [code]
Dong, J., Zhang, J. L., Zeng, S., & Li, F. (2020). Subgroup balancing propensity score. Statistical Methods in Medical Research, 29(3), 659-676. [code]
Zeng, S., Zhang, P., Charles, D., Manavoglu, E.,& Kiciman ,E. Robust Neutral Network for Causal Invariant Feature Extraction. Neural Information Processing Systems 2019 Causal Machine Learning Workshop. [poster]
Feng, F., Li, L., Powers, M., & Zeng, S. A Markov-Switching Autoregressive Model for the Underwriting “Cycle”. Aisa Pacific Risk and Insurance Association Annual Conference, 2017
I am fortunate to work with the following researchers: Fan Li (Duke), Peng Ding (UC Berkeley), Fan (Frank) Li (Yale), Susan Alberts (Duke), Elizabeth Archie (Notre Dame), Stacy Rosenbaum (UMich), Fernando Campos (UTSA), Liz Lange (Duke), Rui Wang (Harvard Medical School), Junni Zhang (Peking University), Serge Assaad (Duke), Chenyang Tao (Duke), Shounak Datta (Duke), Lawrence Carin (Duke), Jason Poulos (Duke), Emre Kiciman (Microsoft), Denis Charles (Microsoft), Pengchuan Zhang (Microsoft), Joel Pfeiffer (Microsoft), Murat Bayir (Microsoft).