1. Large-Dimensional Random Matrix Research Team

The main research focuses on the following two aspects:
(1) When the dimension of a random matrix approaches infinity, the properties of its eigenvalues ​​and eigenvectors are studied, including the limits and limit distributions of eigenvalues ​​and their functions, the directionality and orthogonality of eigenvectors, and the relationship between eigenvalues ​​and eigenvectors and the structure and properties of the matrix.
(2) Using the theory of large-dimensional random matrices, the properties of the overall distribution are inferred from a large amount of high-dimensional observation data, including high-dimensional hypothesis testing, dimensionality reduction of high-dimensional data, high-dimensional variable screening, channel capacity in multi-antenna communication systems, and high-dimensional data analysis and feature extraction algorithms in machine learning.

2. Biostatistics Research Team
This research team focuses on precision medicine, medical image processing, and statistical analysis of latent structure models in high-dimensional matrix data. Key research questions include: statistical learning methods and inference for optimal individualized (dynamic) treatment plans in precision medicine; theoretical and algorithmic research on resampling techniques for big data; and large-scale...

3. Big Data Statistics Research Team
This research direction is driven by real-world data and problems. In response to the characteristics of the big data era, such as large data scale, high variable dimensionality, and complex inter-variable structure, it focuses on how to build structured models to explain and predict big data, as well as developing new theories and methods to process these models. The research content includes structured dimensionality reduction of big data, complex network data analysis, graph models, and Bayesian networks.

4. Computer Experiment Design and Modeling Research Team
The reliability of data analysis conclusions largely depends on the quality of the collected data. Experimental design is an effective means of obtaining high-quality data in scientific experiments. However, due to limitations such as time, cost, destructiveness, and ethics, some experiments cannot be conducted directly and require the use of mathematical models and computer simulations. Our team focuses on research related to computer experimental design, including experimental design and data sampling, statistical modeling, statistical computation, and the application of computer experiments in the field of artificial intelligence.

5. Economic Statistics Research Team
The main research has two aspects: (1) Propose statistical inference methods for econometric models (such as selection models, dynamic panel models, policy effect evaluation models, etc.) to provide analytical tools and methods for economic data analysis; (2) Use statistical methods to conduct empirical analysis of economic data and analyze the economic phenomena and operating laws of the economic system behind the economic data.

6. Educational Statistics Research Team
The main research focuses on two aspects: (1) developing and optimizing educational and psychometric statistical models and methods, such as item response theory models, cognitive diagnostic models, and structural equation models, to gain a deeper understanding of students' learning processes and outcomes. (2) using statistical methods to conduct empirical analysis of educational data, extracting valuable information from a large amount of educational data, revealing the patterns and dynamics behind educational phenomena, and providing a scientific basis for educational policy-making and educational practice.

NOTE: The university may have additional program-specific eligibility requirements.
It is recommended to verify these on the official university website.