Chih-Li Sung

Chih-Li Sung

Assistant Professor, Department of Statistics and Probability

Teaching

STT 997: Advanced Topics in Statistics

PhD-level course, Michigan State University
Semester: 2024 Spring
Textbook: Surrogates: Gaussian Process Modeling, Design, and Optimization for the Applied Sciences

Explore the fundamental concepts of Uncertainty Quantification (UQ) in this special-topic course. Uncertainty is inherent in various fields, from engineering to finance, and understanding its impact is crucial for informed decision-making. Through a combination of theoretical insights and practical applications, this course will cover key UQ principles, modern statistical methods, and computational tools. This course covers the following topics:

  • Gaussian process (GP) regression
  • Space-filling designs and model-based designs
  • Sensitivity analysis
  • Computer model calibration
  • Bayesian optimization
  • Multi-fidelity simulations

STT 481: Capstone in Statistics

Undergraduate course, Michigan State University
Semester: 2023 Spring, 2022 Fall, 2022 Spring, 2021 Fall, 2021 Spring, 2020 Fall, 2020 Spring, 2019 Fall, 2019 Spring, 2018 Fall
Textbook: An Introduction to Statistical Learning with Applications in R

Statistical capstone experiences are essential for statisticians to perform an in-depth analysis of real-world data. Capstone experiences can develop statistical thinking by engaging in a consulting-like experience that requires skills outside the scope of traditional courses: defining a complex problem, analyzing data, building a strong team, and communicating effectively. In this course, selected projects will be given to illustrate special problems encountered by professional statisticians in their roles as consultants, educators, and analysts. This course covers the following topics:

  • problem formulation
  • advanced statistical modeling, preliminary data analysis, and machine learning
  • Statistical software (R)
  • thorough and elaborate statistical analyses of data
  • final presentation and data visualization

STT 801: Design of Experiments

Graduate course, Michigan State University
Semester: 2023 Spring, 2022 Spring, 2021 Spring
Textbook: Experiments: Planning, Analysis, and Optimization, 2nd Edition

Design of experiments (DOE) is the laying out of a detailed experimental plan in advance of doing the experiment. In this course, students will learn various experimental designs and their applications. Students will also learn to analyze data and determine the relationship between potential factors and the output of that process from planned experiments, using the statistical software (R). This course covers the following topics:

  • experimental designs: fractional factorial experiments, Latin squares, orthogonal arrays, robust parameter designs, and other designs
  • data analysis for experimental data: linear regression model, analysis of variance and covariance (ANOVA), analysis of covariance (ANCOVA), random effect model, response surface methodology, and others
  • statistical software: R
  • model interpretation
  • presentation and data visualization