Teaching
STATS 235 — Statistical Machine Learning
Statistical methods for high-dimensional problems: optimization and sampling algorithms; supervised and unsupervised learning; regularization; splines; Gaussian process regression; SVM; tree-based methods; graphical models; neural networks and deep learning — across both frequentist and Bayesian paradigms.
STATS 225 — Bayesian Analysis
Bayesian statistical methods and their applications, with the computational techniques commonly used in Bayesian analysis. Students learn to formulate a scientific question as a Bayesian model and perform inference to answer it.
STATS 230 — Statistical Computing Methods
Writing your own programs for statistical analysis: optimization methods (largely frequentist) and sampling algorithms (largely Bayesian), plus numerical linear algebra, the bootstrap, and other computational tools.
STATS 200B — Intermediate Probability and Statistical Theory
Parameter estimation for statistical inference: probability theory, principles of data reduction, point estimation (method of moments, maximum likelihood, Bayes), and decision theory, from both frequentist and Bayesian perspectives.
STATS 211 — Statistical Methods II
Model assessment and selection; controlling complexity (PCR, PLS, Lasso); basis expansions and splines; GAMs; Gaussian process regression; multilevel models; discriminant analysis; naive Bayes.
STATS 212 — Generalized Linear Models
Exponential family; binomial, multinomial, and Poisson models; logistic and multinomial-logit regression; Poisson and loglinear models; quasi-likelihood; Bayesian GLMs; random effects models.
STATS 275 — Statistical Consulting
Forming a scientific question, translating it to a statistical problem, applying an appropriate method, and reporting findings to non-statisticians. Students collaborate with other scientists at UCI on a specific project.
STATS 205P — Bayesian Data Analysis
Basic Bayesian concepts and methods, with an emphasis on data analysis, for the professional master’s program.
DATA 296P / 297P — Capstone Writing & Communication / Design & Analysis
A paired capstone: 297P covers problem definition, data representation, algorithm selection, solution validation, and presentation of results; 296P covers writing and presenting that work.
STATS 170A / 170B — Project in Data Science
Problem definition and analysis, data representation, algorithm selection, solution validation, and presentation of results, across a two-quarter capstone sequence.
STATS 5 — Seminar in Data Science
An introduction to data science, for entering students.
STATS 7 & 8 — Introduction to Statistics & Biostatistics
Designing scientific studies; exploring data; probability; discrete and continuous distributions; estimation; hypothesis testing; linear regression.