Teaching

I teach statistics and applied mathematics at CSUB with an emphasis on computational thinking, real-world data, and student-centered active learning. I integrate AI tools thoughtfully — only after core concepts are secure — and build Custom GPT tutors to support individualized practice outside the classroom.

Current & Recent Courses

MATH 2200

Elementary Statistics

Introduction to statistical methods with an emphasis on critical thinking, data analysis using R, and real-world applications. Topics include descriptive statistics, probability, inference for proportions and means, ANOVA, and linear regression.

Undergraduate · OER materials · AI-assisted learning tools

MATH 3200

Probability Theory

First course in the mathematical theory of probability and statistics. Topics include combinatorial methods, conditional and marginal probability, discrete and continuous random variables, probability distributions, mathematical expectation, covariance and correlation, asymptotic distributions, and sampling distributions. Uses R for simulations.

Upper-division · Wackerly, Mendenhall & Scheaffer · Fall 2025

MATH 3209

Statistical Measures of Inequality in Society

Introduction to statistical methods stressing critical thinking and awareness of how statistics are applied across disciplines. Individual and group projects with real data. Uses R for data analysis.

Undergraduate · General Education · Spring 2025

MATH 3210

Applied Statistical Computing and Multivariate Methods

Statistical computing course covering R and SAS from first principles through Shiny apps and dashboards. Topics include data management, visualization, PCA, factor analysis, k-means clustering, and multivariate methods.

Graduate · R & SAS · Fall 2024

MATH 4200

Mathematical Statistics

Fundamentals of statistical inference: sampling distributions, estimation theory (sufficiency, efficiency, MLE, method of moments), hypothesis testing, likelihood ratio tests, confidence intervals, and Bayesian methods. Simulation and inference with R.

Upper-division · Proof-based · Spring 2025

MATH 4210

Regression Modeling and Analysis

Advanced course in applied regression analysis. Topics include linear regression, randomization tests, correlation analysis, model diagnostics and remedial measures, matrix algebra notation for regression, variable and model selection techniques. Additional topics may include Poisson regression, logistic regression, path analysis, and forecasting. Uses R or SAS.

Upper-division · Applied · 4 units

MATH 4230

Applied Statistical Methods for Data Science

Advanced statistical methods bridging theory and data science practice. Regularization (ridge, lasso), tree-based methods, random forests, gradient boosting, neural networks, SVMs, and unsupervised learning. Uses the ISLR textbook with R and Python.

Upper-division · Statistical Data Science concentration

Teaching Philosophy

My teaching is rooted in the belief that education has the power to transform lives — a conviction shaped by my mother, who spent over 35 years teaching in rural schools in Sri Lanka, changing the trajectories of countless students and families.

My approach centers on four kinds of interaction. Student-teacher interaction comes first: I learn every student’s name, create a comfortable classroom atmosphere, and make myself approachable. I treat every question the same, whether simple or complex, because I never want a student to feel insecure about asking. Student-subject interaction means showing students why statistics matters before diving into formulas — I motivate concepts with real-world examples tailored to the class composition, from stock markets and cryptocurrencies to environmental data. Peer-to-peer interaction happens through group projects, collaborative mini-analyses, and in-class problem solving where students teach each other. Student-real world interaction prepares students for life after the classroom through oral presentations, guided reports, and conversations about higher education and careers.

I use AI deliberately and ethically — Custom GPT tutors support coding practice and concept review, but only after students have built foundational understanding. As I tell my students: “Anyone can google the steps to a hypothesis test, but you need to understand the basics to interpret the result and make inferences.”

We also have to accept the reality that the industry and job market have changed dramatically over the last couple of years. It is my duty to prepare my students for this new world — not just with statistical theory, but with computational skills, AI literacy, data science workflows, and the critical thinking needed to work alongside AI rather than be replaced by it. This is a central part of my teaching philosophy and why I invest heavily in building AI-integrated learning experiences.

AI Tools for Students

I develop Custom GPT tutors to support my courses:

  • R Tutor for MATH 2200 — Learning assistant for R coding in introductory statistics
  • MATH 4200 AI Assistant — Guided problem-solving for mathematical statistics
  • LaTeX Converter — Helps students typeset mathematical work
  • MATLAB / R / Python Learning Assistants — Language-specific coding support
  • MathBuddy Jr. — Accessible math practice tool
  • Study Coach GPT — General study strategies and organization

Teaching Innovations

  • OER Development — Recognized by CSUB Affordable Learning Solutions (2024–25) for providing zero-cost materials and building AI tools that improve student learning
  • ELEVATE Project — Co-PI on California Learning Lab grant developing AI-enhanced learning experiences for STEM education
  • CSUB JupyterLab Cloud — Launched browser-based access to R, Python, and VS Code for students via CAL-ICOR partnership
  • AI Instructional Module — Co-developed with Kim Mishkind for first-year seminar (BA 1028), teaching AI literacy and prompt engineering
  • Statistical Data Science Concentration — Collaborated with Drs. Montoya and Zeng to revise the statistics concentration and design MATH 4230

Student Mentorship

I am deeply committed to undergraduate research mentorship:

Program Year Students Project
SURE (Chevron) Summer 2025 J. Rosas, J. Rodriguez, C. Rodriguez, R. Gamez Local LLM applications for education
CV Pathway Summer 2025 E. DeJesus, N. Gallego Air pollution and fertility patterns
Student Research Scholars 2024–25 1 student How Present is ChatGPT at CSUB?
CV Pathway Summer 2024 T. Regpala, J. Rodriguez Aguilar Air pollution research

For Students

Office hours: See your course Canvas page for current times, or email me at ayatawara@csub.edu to schedule an appointment.

Recommendation letters: I’m happy to write letters for students I know well. Please provide at least 3 weeks’ notice, your CV/resume, the program description, and a brief note about what you’d like me to emphasize.