# Teaching

Most of the materials for courses I teach are maintained on course websites available after you register for the course (e.g., on Canvas). Here I have listed minimal overviews of courses I have taught.

### Taught at Clemson University

#### MATH 3020 – Statistics for Science and Engineering (Syllabus)

Introductory statistics with an emphasis on science and engineering applications. This is essentially a standard introductory statistics course covering descriptive statistics, one- and two-sample inference, simple linear regression, and ANOVA. Additional topics include calculus-based elementary probability, including density/distribution functions and standard probability distributions, including the Binomial, Poisson, Normal, and Gamma densities. I personally try to also include an overview of Poisson processes. Taught at the level of Montgomery, Runger, and Hubele.

#### MATH 4000 – Theory of Probability (Syllabus)

An advanced undergraduate-level course in probability theory. Topics include axiomatic probability; conditional probability and Bayes’ rule; discrete/continuous random variables; probability distributions; joint distributions and transformation theory. Taught at the level of A First Course in Probability, by Ross.

#### MATH 4020 – Statistics for Science and Engineering II (Syllabus)

A follow up course to MATH 3020. This course is more open-ended in terms of the material that can be covered, but it typically builds on introductory material to cover modern statistical methods that are commonly used in practice. When I teach this course, I cover statistical learning. This includes multiple regression, classification, boostrapping and cross-validation, regularization / shrinkage, and spline regression. Taught at the level of An Introduction to Statistical Learning with Applications in R, by James, Witten, Hastie, and Tibshirani.

#### MATH 4090 – Design of Experiments for Science and Engineering

This is an introductory course on the design and analysis of experiments, with an emphasis on techniques and examples driven by problems in engineering and the physical sciences. Topics include replication and blocking principles, one- and multi-way layouts, Latin squares, full and fractional factorial designs, including relevant R packages. Taught at the level of Wu and Hamada.

#### MATH 8010 – General Linear Hypothesis I (Syllabus)

A first year graduate-level course in the theory of linear models. There are different ways this course has been taught, but I tend to favor the geometric/projection-based approach. Topics include a review of linear algebra including vector spaces, projections, systems of equations and symmetric matrices; distributions of linear and quadratic forms in random vectors; estimation and inference in the full-rank linear model. Taught at the level of Rencher and Schaalje, or Stapleton.

#### MATH 8020 – General Linear Hypothesis II (Syllabus)

A direct continuation of MATH 8010. This course is offered purely as an elective, so the topics can be chosen more freely. My goal in this course is to present to interested students the non-full rank (i.e, ANOVA) model in more detail, the Bayesian linear model, mixed effects models, and some categorical data analysis/GLMs. I draw from several different texts for this material.

#### MATH 8050 – Data Analysis (Syllabus)

A graduate course in applied linear modeling, assuming a background in elementary statistics. This course is part of the statistics curriculum for MATH graduate students, but it also acts in part as a service course for a wide range of disciplines. In addition to the math sciences department, students in this course come from, e.g., computer science, engineering, physics, and biology. The goal of this course is to establish a solid understanding of the fundamentals of linear models as applied to real data analysis, with an emphasis on practical implementation issues as opposed to the theoretical foundations (which is covered in MATH 8010). Topics include simple linear/multiple linear regression, including the matrix approach and understanding the design matrix; extra sums of squares; polynomial regression, categorical predictors, and interaction; model diagnostics; model selection and validation; logistic regression, Poisson regression, and generalized linear models; additional advanced regression topics, if time permits. Taught at the level of Kutner, Nachtsheim, Neter, and Li.

### Taught at The University of Georgia

#### STAT 2000 – Introductory Statistics

First or second-year undergraduate course in elementary statistics. This is a coordinated course with common syllabus, exams, labs, and homework assignments. Topics include descriptive statistics, sampling and survey methods, correlation and regression, contingency tables, sampling distributions, one- and two-sample inference. Taught at the level of Agresti and Franklin.

#### STAT 4220 – Applied Experimental Designs (Syllabus)

Undergraduate level course in the design and analysis of experiments, assuming at least two semesters of college-level statistics as a prerequisite. Topics include randomization, blocking, replication, one- and two-way layouts, Latin squares, repeated measures; the necessary ANOVA for such designs, including contrasts and multiple comparisons procedures; fixed and random effects. Taught at the level of Introduction to Design and Analysis of Experiments,  by Cobb.