Course notes

Lecture 1: What is EDA?
[R code]   [data]

Lecture 2: Univariate data visualization
[R code]   [Reading: Cleveland pp. 16-22, 24-25, 29-33 and ggplot2 book Sections 2.1-2.8]

Lecture 3: Comparing univariate distributions and tidy data
[R code]   [Reading: Tidy data section of R for Data Science]

Lecture 4: Computational tools and transformations
[R code]   [Reading: R for data science chapters 10 and 12, Cleveland pp. 42–67]   [data]

Lecture 5: Building Simple Models
[R code]   [Reading: Cleveland pp. 34-41, 68-79]

Lecture 6: ggplot, more formally
[R code]   [Reading: ggplot paper]  [data 1, data 2, data 3]

Lecture 7: Bivariate data
[R code]   [Reading 1, Reading 2]  [data]

Lecture 8: Flexible modeling for bivariate data
[R code]   Reading: Cleveland pp. 91-110

Lecture 9: Smoothing part II
[R code]   [Recording]

Lecture 10: Robust regression and comparing bivariate datasets
[R code]

Lecture 11: Interactions and coplots for trivariate data
[R code]   Reading: Cleveland pp. 184-190, 194-199, 204-205

Lecture 12: More interactions, coplots, and modeling
[R code]  

Lecture 13: Level and contour plots
[R code]   Reading: Cleveland pp. 228-241, 245-248, 257-266, 270

Lecture 14: Model-building with a moderate number of variables
[R code]   [data]

Lecture 15: Logistic regression
[R code]   [data]

Lecture 16: Logistic regression 2
[R code]   [data]

Lecture 17: Count responses and Poisson regression
[R code]

Lecture 18: Categorical data and contingency tables
[R code]   Reading: vcd tutorial

Lecture 19: Ordered and unordered categorical responses
[R code]   [data 1, data 2]

Lecture 20: EDA and the problem of multiple comparisons
[R code]   Reading: Gelman and Loken, “The garden of forking paths”

Lecture 21: Background for hypervariate data and biplots
[R code]   Reading: Greenacre chapter 1

Lecture 22: Singular value decomposition and reduced-rank biplots
[R code]   Reading: Greenacre chapter 5

Lecture 23: Principal components analysis
[R code]   Reading: Greenacre chapter 6

Lecture 24: Scree plots and choosing the number of dimensions
[R code]   [data 1, data 2, data 3]

Lecture 25: Multi-dimensional scaling
[R code]   [data]

Lecture 26: Linear discriminant analysis
[R code]