Hello/你好! I am an Assistant Professor in Statistics at Georgia State University. I am also a faculty member of Brains & Behavior (B&B) in its Neuroscience Institute and affiliated with the Center for Cosmic Ray Studies.
I was a postdoctoral scholar at McGill University jointly with the University of Waterloo, kindly sponsored by the Canadian Statistical Sciences Institute (CANSSI). I am also affiliated with Mila - Quebec AI Institute and UW’s Health Data Science Lab.
My office is: Room 1407, 25 Park Place.
I currently serve as an associate editor of Statistics and Computing.
Note: For reference letter, please do not contact me unless (1) you get at least an A/95% or (2) I know you well personally. If so, please use the subject line “Reference Letter Request - Your Full Name” in your email.
North America Taiwanese Statistician Map: I create a Taiwanese @ NA researcher map to visualize the Taiwanese researcher in the field of statistics in North America.
UWaterloo Researcher Map: I create a researcher map to visualize the researcher’s location from the Department of Statistics and Actuarial Science at the University of Waterloo.
Research Interests
My research interests include:
- Functional data analysis.
- Statistical machine learning and high-dimensional statistical inference.
- Dependence modeling.
- Optimal design of experiments.
- Large language model (LLM) alignment.
- Retrieval-augmented generation (RAG) with uncertainty quantification.
Applications include drug discovery and development, toxicology, neuroscience, and cosmic ray studies.
* indicates students or postdocs.
Preprint
- Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
- AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing
- Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning
- ragR: Retrieval-Augmented Generation and RAG Assessment in R
- Single and multi-objective optimal designs for group testing experiments with a focus on screening for an infectious disease
- FTSgof: White noise and goodness-of-fit tests for functional time series in R
- CVXSADes: a stochastic algorithm for constructing optimal exact regression designs with single or multiple objectives
2025
- Positive and unlabeled data: model, estimation, inference, and classification
- Variable selection in multivariate functional linear regression
2023
- Functional spherical autocorrelation: a robust estimate of the autocorrelation of a functional time series
2022
- Evaluating real-time probabilistic forecasts with application to National Basketball Association outcome prediction
2021
- Properties of optimal regression designs under the second-order least squares estimator
Thesis
- Methods in functional data analysis: forecast evaluation, robust serial dependence measures, and a spatial factor copula model
- Optimal regression design under second-order least squares estimator: theory, algorithm and applications
* indicates students or postdocs.
Optimal Design of Experiment
-
A R package for computing optimal regression designs under the second-order least-squares estimator
-
A R package for computing optimal regression designs for group testing experiments
-
cvxDesign [GitHub]A R package for computing optimal regression designs with single or multiple objectives through convex optimization
-
optDesign [GitHub]A MATLAB toolbox to compute optimal regression design
Functional Data Analysis
-
A R package for white noise and goodness-of-fit tests for functional time series
-
A R package to Evaluating the probabilistic forecasts between competitive forecasters
AI and Machine Learning
-
A R package for Retrieval-Augmented Generation and RAG Assessment
Personal
-
yehUtil [GitHub]A R package for knitting some RMarkdown reports and other usages
PhD Student
-
Wenpu is working on cost-effectiveness analysis related problems and is co-supervised with Professor Gengsheng Qin
Research Master Student
-
Kalen is working on optimal design problems
-
Seoyoung Kim, Applied Statistics[website]Seoyoung is working on human annotation and retrieval-augmented generation (RAG) problems.
Extenal Student Collaborator
-
Shaohui Wang, Ph.D. Candidate at J. Mack Robinson College of Business, GSU[website]
-
Chang Qu, Ph.D. Candidate at the University of OttawaChang is working on Privacy-Awared Optimal Design Problem
Past Members (3)
-
Zhili Lu (2026), Applied Statistics[website]
-
Sierra worked on classification problem on GSU Pitchers in baseball games
-
Yi Xing Hu (2026), MS.c. at McGill UniversityYi Xing worked on gene/cell regulation problems using Reinforcement Learning
Computing
-
MFCF computing resource shortguide 2025-02-20Demonstrate how to use UW MFCF computing resources, including VPN, server connection, and running R scripts
Georgia State University
-
GSU Resource 2026-05-10List of many useful resources in Georgia State University
Personal
-
Job Market reflection 2026-05-08For Tenure-Track Statistics Professorship in North America
Research
-
Optimal Regression Design 2026-05-09A short tutorial to optimal regression design