Visualizing High-Dimensional Data: MDS, PCA, t-SNE, and UMAP

About this Class

Visualizing high-dimensional data presents unique challenges. While Principal Component Analysis (PCA) is a widely used approach, several powerful alternatives exist including Multi-Dimensional Scaling (MDS), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP). This demo-based session provides practical examples of generating each of these visualizations using R/RStudio. A working knowledge of R and RStudio is recommended but not required to attend this event.

Complementary Event: This session pairs with the Statistics for Lunch talk, Visualizing High-Dimensional Data: MDS, PCA, t-SNE, and UMAP, also presented by Brian Luke, Ph.D. (Advanced Biomedical Computational Science, FNLCR). That talk explores the conceptual differences between these methods without heavy mathematics, helping you determine which visualization is best suited for your data. Attending both sessions is encouraged for a comprehensive understanding of the topic.