689 Statistical Computing with R and Python was taught Spring 2018 at Texas A&M University by James Long. This website is no longer maintained but is available for reference purposes.

General

• Syllabus
• Setting Up Computing Environment (Python, R, Jupyter Notebooks, etc.)
• Project Information
• Student Project Slides

Reading

Suggested reading will be given in class and in Jupyter notebook files. All texts are available either through TAMU library or on the internet via the links provided.

• Numerical Analysis for Statisticians by Kenneth Lange (advanced, subset of chapters 5,7,9–14,19,20,22,26)
• Computational Statistics by Gentle (intermediate, mostly parts 1 and 2)
• Advanced R by Hadley Wickham (advanced): This is a good book if you want to figure out what R is really doing under the hood.
• Python Data Science Handbook by Jake VanderPlas (intermediate)
• R for Data Science by Grolemund and Wickham (intermediate)

Data Sets

• Netflix
• NBA Scores 2002-2003
• Circadian Gene Identification

In Class Notes and Demos

All notes are written in Jupyter notebooks. To execute code and markdown in these notebooks you must have Jupyter notebook software installed on your computer. The links named static open the notebooks in an online Jupyter notebook viewer which allows users to view, but not execute, code and Markdown.

• Introduction to Notebooks, R, and Python, static

• Brief Language Introduction
  • R, static
  • Python, static
• Generating Uniform Random Deviates
  • R, static
  • Python, static
• Generating Non-Uniform Random Deviates
  • Methods (in Python), static
  • von Mises (in Python), static
• Algorithm Complexity and Big O Notation, static
• git, static
• Linear Regression Intro, static
• Linear Regression R Implementation, static
• Basis Expansions and Splines
  • R, static
  • Python, static (in progress)
• Block Relaxation for Fitting Poisson Scoring Model to NBA 2002-2003 Season, static
  • Data Set Background and Cleaning
• Block Relaxation for k–Means Clustering, static
• One Dimensional Root Finding, static
• Newton’s Method (slides)
• Gradient Ascent
  • Logistic Regression Fit with Gradient Ascent, static
  • Logistic Regression with Mislabeled Data, static
• Parameter Estimation, Prediction, and Sampling Distributions (slides)
• MLEs, Fisher Information, and Hessians (slides)
• Newton’s Method with HIV Data, static
• Sensor Network Localization and BFGS, static
• Netflix Prize and Collaborative Filtering (slides)
• Bayesian Statistics
  • Bayesian Intro, static
  • Bayesian Conjugate Models, static
  • Metropolis Hastings MCMC, static
  • Metropolis for Logistic Regression, static
    • R code for Logistic Metropolis
    • Data file for R code
  • Metropolis for Cryptography
    • Metropolis for Decoding, static
    • Creating the Coded Message, static
  • Gibbs Sampler for the Normal Model, static
  • Hierarchical Models
    • Overview (slides)
    • Coagulation Example (zipped folder, code in R)
  • Stan for MCMC, static
  • Hierarchical Batting Average Model with Stan, static

Homeworks

Homeworks have been removed. Contact the instructor if you would like to see them.