Prospective Students

Thank you for your interest in joining my research group. I work with students who are curious about statistical genetics, high-dimensional statistics, data science, computational methods, and scientific applications of AI.

Before sending an email, please read this page carefully. It is meant to help you decide whether the group is a good fit and to make our first conversation more productive.

When to Contact Me

The earlier you contact me, the better. Early contact gives you time to build the necessary research skills and a solid foundation.

If you plan to apply for the PhD program, please contact me at least six months before submitting your application. This gives us enough time to discuss your research interests, preparation, and potential project fit.

What to Include in Your Email

Please send a concise email with:

  • A brief introduction of your background and current program.
  • Your CV and transcript.
  • Your long-term goals (for example, whether you are determined to become a scientist; you try to figure out how knowledge is formulated).
  • [Optional] Your expected application year and program.
  • [Optional] The research directions in this group that interest you.
  • [Optional] One or two research experiences, course projects, papers, or technical topics that shaped your interests.
  • [Optional] Your current preparation in statistics, mathematics, computing, and genetics or genomics.

Generic emails are hard to evaluate. A good email does not need to be long, but it should make clear why you are interested in this group specifically.

You do not need to master everything below before contacting me. However, these topics are useful foundations for research in this group, and prospective PhD students should be willing to learn them seriously.

Statistics and Regression

  • Linear regression, least squares, bias-variance tradeoff, residuals, diagnostics, and interpretation.
  • Regularized regression, including ridge regression, Lasso, elastic net, variable selection, and shrinkage.
  • Generalized linear models, including logistic regression and Poisson regression.
  • Fixed effects, random effects, mixed effects models, variance components, and when each model is appropriate.
  • Model selection, cross-validation, prediction error, overfitting, and uncertainty quantification.
  • Multiple testing, false discovery rate, p-values, confidence intervals, and hypothesis testing.

Probability and Asymptotics

  • Random variables, common distributions, conditional expectation, variance, covariance, and correlation.
  • Law of large numbers, central limit theorem, delta method, and basic asymptotic reasoning.
  • The main modes of convergence: almost sure convergence, convergence in probability, convergence in distribution, and convergence in mean square or in Lp.
  • How these modes of convergence differ, and which implications hold among them.

Linear Algebra and Optimization

  • Vectors, matrices, rank, projection, orthogonality, norms, and positive definite matrices.
  • Eigenvalues, eigenvectors, eigendecomposition, and their statistical interpretations.
  • Singular value decomposition and its connection to low-rank approximation.
  • Principal component analysis, including interpretation, scaling, and limitations.
  • Convex optimization basics, gradients, Hessians, constrained optimization, and penalized objectives.

Statistical Genetics and Genomics

  • Basic genetics terminology, including SNPs, alleles, genotype coding, linkage disequilibrium, and population structure.
  • Genome-wide association studies, marginal association testing, covariate adjustment, and multiple testing.
  • Polygenic risk scores, heritability, genetic correlation, and related interpretation issues.
  • High-dimensional omics data, such as gene expression, eQTLs, single-cell data, and multi-omics integration.
  • Reproducibility, batch effects, confounding, and careful biological interpretation.

Computing

  • Comfortable use of R or Python for data analysis.
  • Reproducible workflows, version control with Git, and clear documentation.
  • Basic command-line skills and the ability to work with large data files.
  • Simulation studies, numerical experiments, and careful checking of computational results.

What I Look For

I value curiosity, intellectual honesty, persistence, clear communication, and the ability to learn independently. Prior research experience is helpful, but it is not the only criterion. I am especially interested in students who enjoy both methodological thinking and real scientific data problems.

When you contact me, I may suggest a paper, textbook chapter, dataset, or small project for you to study before we meet. This helps both of us evaluate fit in a concrete way.

Before Applying

Please spend time reading about the group’s research areas and thinking about what kind of problems you would like to work on. A PhD is a long training process, and fit matters on both sides. The goal of early contact is not only admission, but also making sure that the research direction, advising style, and expectations are aligned.