Research Interests

• Causal Inference
• Machine Learning
• Mediation Analysis
• Dimension Reduction/Variable Selection 

My research interest lies in causal inference, machine learning and the interface between the two. I highly appreciate the interdisciplinary nature of causal inference and aim to develop theoretically sound methods for data-driven problems. My recent focus is on the development of variable selection/dimension reduction procedures to adjust for confounding in observational studies in a high-dimensional setting. In addition, I have developed innovative machine learning algorithms for the modeling of propensity scores for binary, multi-level and continuous treatments. Meanwhile, I'm also working on causal mediation analysis, which examines how a treatment/intervention  affects the outcome through  one/multiple intermediate variables. Applications of my research lie in biomedical studies, public health and social sciences.
​

Publications 
1. Propensity Score-Based Methods

• Lin, L., Zhu, Y. & Chen, L. (2018), Causal inference for multi-level treatments with machine-learned propensity scores, Health Services & Outcomes Research Methodology, accepted.​
• Zhu, Y., & Lin, L. (2016), Propensity score modeling and evaluation. In H. He, P. Wu, & D.-G. Chen (Eds.), Statistical Causal Inferences and Their Applications in Public Health Research. Springer. 
• Zhu, Y., Schonbach, M., Coffman, D.L., Williams J.S. (2015), Variable Selection for Propensity Score Estimation via Balancing Covariates, Epidemiology, 26(2), e14-15. 
• Zhu, Y., Coffman, D.L. and Ghosh, D. (2015), A Boosting Algorithm for Estimating Generalized Propensity Scores with Continuous Treatments, Journal of Causal Inference, 3(1), 25-40.
• Zhu, Y., Ghosh, D., Mitra, N. and Mukherjee, B. (2014), A Data-Adaptive Strategy for Inverse Weighted Estimation of Causal Effects, Health Services & Outcomes Research Methodology, 14(3), 69-91. 

 2. Dimension Reduction/Variable Selection for Causal Inference

• Luo, W. and Zhu, Y. (2019), Matching Using Sufficient Dimension Reduction for Causal Inference, Journal of Business and Economic Statistics, accepted.
• Luo, W., Wu, W. and Zhu, Y. (2019), Learning Heterogeneity in Causal Inference Using Sufficient Dimension Reduction, Journal of Causal Inference, 7(1).
• Luo, W., Zhu, Y. and Ghosh, D. (2017), On Estimating Regression-based Causal Effects Using Sufficient Dimension reduction, Biometrika, 104(1), 51-65.
• Ghosh, D, Zhu, Y., and Coffman, D.L. (2015), Penalized Regression Procedures for Variable Selection in the Potential Outcomes Framework, Statistics in Medicine, 34(10), 1645-1658.

3. Balance in Causal Inference

• Xie, Y., Cotton, C. and  Zhu, Y. (2020), Multiply Robust Estimation of Causal Quantile Treatment Effects,  Statistics in Medicine, 39 (28), 4238--4251.
• Zhu, Y., Savage, J.S., and Ghosh, D. (2018), A Kernel-based metric for balance assessment, Journal of Causal Inference, 6(2).
• Xie, Y., Zhu, Y., Cotton, C. and Wu, P. (2017), A model averaging approach for estimating propensity scores by optimizing balance, Statistical Methods in Medical Research, doi:10.1177/0962280217715487. 

4. Causal Mediation Analysis

• Ye, Z.,  Zhu, Y. and Coffman, D. (2021). Variable Selection for Causal Mediation Analysis Using LASSO-based Methods,  Statistical Methods in Medical Research, 30 (6), 1413--1427.
• Coffman, D. L., MacKinnon, D. P., Zhu, Y., & Ghosh, D. (2016), A comparison of potential outcomes approaches for assessing causal mediation. In H. He, P. Wu, & D.-G. Chen (Eds.), Statistical Causal Inferences and Their Applications in Public Health Research. Springer.​
• Zhu, Y., Ghosh, D., Coffman, D. L., Savage J. S. (2016), Estimating Controlled Direct Effects of Restrictive Feeding Practices in the `Early Dieting in Girls' Study, Journal of Royal Statistical Society, Series C, 65(1), 115-130.

​5. Interdisciplinary Research

• Costello, J., Li, Y., Zhu, Y. et al. (2021). Using Conventional and Machine learning Propensity Score Methods to Examine the Effectiveness of 12-step Group Involvement Following Inpatient Addiction Treatment,  Drug and Alcohol Dependence, 227, 168943.
• Arani, A., Hu, P., Zhu, Y. (2021). Fairness-Aware Link Optimization for Space-Terrestrial Integrated Networks: A Reinforcement Learning Framework,  IEEE Access, 977624--77636.
• Arani, A., Azari, M. , Hu, P., Zhu, Y. et al. (2021). Reinforcement Learning for Energy-Efficient Trajectory Design of UAVs,  Internet of Things. ​
• Arani, A., Hu, P., Zhu, Y. (2021). Re-envisioning Space-Air-Ground Integrated Networks: Reinforcement Learning for Link Optimization,  IEEE International Conference on Communications (ICC): Next-Generation Networking and Internet Symposium, 1--7.