Data Science Research Assistant

Yiqiao Jin

** * ******* ***, **. Louis, MO ***** • *.******@*****.*** • +1-314-***-****

EDUCATION

Washington University in St. Louis, Department of Statistics & Data Science St. Louis, MO Ph.D. in Statistics Aug 2024 - May 2029 (Expected) Course Advisor: Dr. Likai Chen & Dr. Xuming He

Research Advisor: Dr. Nan Lin & Dr. Linying Zhang & Dr. Mengxin(Maxine) Yu Research Interest: Heterogeneous Treatment Effect; Mediation Analysis; Federated Learning; Modal Collapse Fudan University, School of Data Science Shanghai, China Master of Science in Applied Statistics Aug 2022 - Jun 2024 Honors & Awards: Outstanding Freshman Scholarship

Thesis: Causal Mediation Analysis with Time-varying Exposures, Mediators and Outcomes Advisor: Dr. Bo Fu

Shanghai Normal University, Mathematics & Science College Shanghai, China Bachelor of Science in Statistics [Highest Honor Degree, Graduated 1st in Class] Aug 2018 – Jun 2022 Honors & Awards: National Scholarship, Professional Scholarship, Outstanding Undergraduate Thesis Award Thesis: Probabilistic Properties and Numerical Approximation of the Folded Normal Distribution Advisor: Dr. Xiaoqing Pan

PUBLICATION

Lu, B., Jin, Y., Fu, B. (2025+). Causal Time Series Mediation Analysis of MPS Effects on CFP through Speculative Powers. Manuscript in Preparation

Liu, X., Jin, Y., Yang, Y., & Pan, X. (2023). Properties and Estimations of a Multivariate Folded Normal Distribu- tion. Mathematics, 11(23), 4860. https://doi.org/10.3390/math11234860 Zeng X., Zhang X., Jin Y., Huang L., Fu B. (2022+). Specific Allergen Immunotherapy Can Greatly Reduce the Need for Systemic Glucocorticoids in Moderate to Severe Allergic Diseases: a Population-Based Study. Manuscript in Preparation

EXPERIENCE

WashU Institute for Informatics, Data Science and Biostatistics St. Louis, MO Graduate Research Assistant, Advisors: Dr. Nan Lin & Dr. Linying Zhang May 2025 - present Individual Project, Tool Utilized: R, Python

• Analyzed a multi-site EHR cohort (90K+ patients; 60K+ covariates) to estimate heterogeneous treatment effects on time-to-event outcomes, comparing two antihypertensive drugs.

• Led a literature review (50+ papers) across heterogeneity/CATE/meta-learners/federated learning, synthesizing gaps that motivated a new algorithm and in-prep manuscript.

• Designed a privacy-preserving Fed R-Learner that performs local/cross-site cross-fitting and quantifies CATEs across multi-sites without patient-level sharing.

• Empirically exploring lower L2 loss for federated vs. centralized R-Learners in cross-site heterogeneous settings on synthetic, IHDP, and ACIC2016 datasets.

1

Fudan University, School of Data Science Shanghai, China Research Assistant, Advisor: Dr. Bo Fu Oct 2023 - July 2024 Individual Project, Tool Utilized: R

• Extended the framework of Granger causal mediation analysis to simultaneously consider an exposure-mediator interaction and time-varying covariates.

• Explored the relationship between the error terms of linear structural equation models and spatiotemporal dependence modelling.

• Carried out experiments on a variety of synthetic and empirical datasets to further illustrate the advantages of the methodology.

Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine Shanghai, China Visiting Student, Research Assistant, Advisor: Dr. Lisu Huang Jun 2022 - Jun 2023 Collaborative Project, Tool Utilized: R, SAS, SQL

• Cleaned, harmonized, and joined 100+ cohort tables to EHR datasets (1B+ rows; 10K+ variables) for downs- tream modeling.

• Curated cohorts, performed propensity-score matching, and fitted proportional hazards model to estimate the short-/long-term impact of allergen immunotherapy on steroid exposure and respiratory infections. Shanghai Normal University, Mathematics & Science College Shanghai, China Research Assistant, Advisor: Dr. Xiaoqing Pan Nov 2021 - Feb 2023 Individual Project, Tool Utilized: R

• Derived explicit marginal and conditional density functions of a multivariate folded normal distribution (FN).

• Utilized Gibbs sampler and Hamiltonian Monte Carlo to generate random samples from FN.

• Implemented the estimation and imputation procedure in a user-friendly R package, FNMLE. ACTIVITIES

WashU American Statistical Association (ASA) Student Chapter St. Louis, MO President Sep 2024 - Present

• Organize the SDS Skills & Professional Advancement (SPA) Series, helping statistics students transition to careers in industry and academia.

• Organized ASA Statistics Day at WashU in collaboration with ASA St. Louis Chapters and the ASA Mid- Missouri; Moderated the career panel and volunteered at the student poster competition. Uncertainty Quantification and Synthetic Data Reading Group St. Louis, MO Member Sep 2024 - May 2025

• Conducted literature reviews and delivered presentations on using traditional statistical methods and modern large models for simulation-based inference.

Short Course of Joint Conference On Statistic and Data Science in China 2023 & PKU Stat-Center Summer School Beijing, China

Summer School Student Jul 2023

• Engaged in academic presentations, discussions and conferences within the fields of statistics and data science. Mathematical Modeling on Health Care at SHNU 2023 Shanghai, China Conference Assistant May 2023

• Prepared conference materials, coordinated conference logistics and housing, and managed front desk operations. SKILLS & INTERESTS

Technical: R, LATEX, SQL, SAS, Python

Language: Mandarin (native), English (fluent)

Interests: Light music, Table tennis

2

Contact this candidate