Practicum in Applied Statistics: Statistical Computing (APSTA-GE 2352)
A course in R as a programming language. Programming skills are taught through the analysis, design, and implementation of algorithms, with special attention paid to modern statistical algorithms
This course will introduce the student to statistical programming and simulation using R. Students will first understand variables, data structures, program flow (e.g., conditional execution, looping) and functional programming, then apply these skills to answer interesting statistical questions involving the comparison of groups. Most statistical analysis will be motivated via simulations, rather than mathematical theory. The course content (programming and data analysis) requires significant outside reading and programming.
This course is designed to treat R as a programming language. Programming skills are taught through the analysis, design, and implementation of algorithms, with special attention paid to modern statistical algorithms (e.g., gradient descent, k-Means clustering, Markov Chain Monte Carlo). Time will also be spent on optimization techniques (e.g., vectorization and parallelization) useful for statistical analysis. Everything done in this course will be implemented in base R. Notable exceptions include the use of the ggplot2 library for visualization and libraries like MASS for sampling from distributions. Students must implement algorithms, write unit tests, and debug from scratch using the tools available in R.