Stanford MS&E 226 – Fundamentals of Data Science

Lecture Notes – 2026

• Lecture 1: Course introduction

  • R Markdown notebook

• Lecture 2: Introduction to prediction

  • R Markdown notebook

  • R Shiny app for polynomial regression

Further current-year materials will be added as they are released.

Lecture Notes – 2025

These previous-year materials remain available until their 2026 replacements are released.

• Lecture 3: Train-validate-test

  • R Markdown notebook

• Lecture 4: Cross validation

• Lecture 5: Classification

  • R Markdown notebook

• Lecture 6: An optimization view of learning algorithms

• Lecture 7: The bias-variance decomposition

  • The flights data used for this lecture is available on Canvas (courtesy of Bureau of Transportation, processed using the R anyflights package).

  • R Markdown notebook

  • R Shiny dashboard for sampling distribution of sample mean

  • R Shiny dashboard with a bias-variance “tradeoff”

  • R Shiny dashboard with no bias-variance “tradeoff”

  • R Markdown notebook explaining previous dashboard

• Lecture 8: Introduction to frequentist statistical inference

• Lecture 9: Standard errors and confidence intervals

  • R Shiny app for normal distribution

  • R Shiny app for confidence intervals for sample mean (flights data)

  • R Shiny app for confidence intervals for sample mean (binary data)

• Lecture 10: The bootstrap

  • R Markdown notebook

• Lecture 11: Hypothesis testing

  • R Shiny app for p-values for binary data

  • R Shiny app for p-values for t statistic

  • R Shiny app for FPP and power for t statistic

• Lecture 12: Beyond single hypothesis tests

• Lecture 13: Introduction to causal inference

• Lecture 14: Regression analysis of experiments

  • R Markdown notebook

• Lecture 15: Causal inference from observational data

  • R Markdown notebook

  • R script for AIPW simulation

• Lecture 16: Bayesian inference and decision making

  • R Shiny app for Bayesian posterior for binary data

  • R Shiny app for Bayesian posterior for normal data

Optional Lectures

• Model scores (Optional)

• Model selection using model scores (Optional)

• F test (Optional)

• Experiment design (Optional)

• Instrumental variables (Optional)