Classification, Modeling, and Inference in R

This unit introduces applied supervised and unsupervised modeling techniques and foundational inferential statistics in R. Students will use Rattle and R packages to build, tune, and evaluate decision trees, SVMs, and neural networks, while also performing t-tests, z-tests, variance checks, and creating reproducible visualizations with ggplot2 to support projects.

Learning Objectives

• Analyze and visualize tabular datasets in R using summary statistics, medians, frequency exploration, and ggplot2 to identify patterns and prepare data for modeling
• Apply inferential statistical tests in R—including independent and paired t-tests, z-tests, and tests for equal variances—and interpret p-values, confidence intervals, and practical significance
• Construct, tune, and evaluate classification models (decision trees, support vector machines, neural networks) using R and Rattle; compare model performance with confusion matrices, accuracy, and other relevant metrics
• Demonstrate reproducible workflow practices by installing and managing R packages, using RStudio/Rattle tools, and documenting end-to-end project analyses for guided datasets