Package index • coursekata

Visualizing distributions and variation

Make counts, spread, and portions of a distribution visible: countable histograms, distribution part functions for shading (with cutoff markers), a standard deviation ruler, and overlays that mark a distribution’s mean and the process that generated it.

gf_sd_ruler() experimental: Add a Standard Deviation Ruler to a Plot
StatSdRuler: Measure one standard deviation of the outcome, anchored at its mean
gf_squareplot() experimental: Countable-Rectangle Histogram
StatSquareplot: Bin observations the way ggplot2::stat_bin() does
GeomSquareplot: Draw one countable rectangle per observation
middle() outer() tails() lower() upper() experimental: Find a percentage of a distribution
show_cutoffs() experimental: Add Cutoff Markers to a Distribution
StatCutoff: Compute a distribution part's empirical quantile cutoffs, per panel
show_mean() experimental: Mark a Distribution's Mean
show_dgp() experimental: Frame a Sampling Distribution With Its Data Generating Process

Visualizing models

Layer models, their coefficients, residuals, reductions, and squares of both onto ggformula plots.

gf_b() gf_coef(): Annotate a model's coefficients on a plot
gf_model(): Add a model to a plot
gf_reduce(): Add Reduction Lines to a Plot
gf_resid(): Add Residual Lines to a Plot
gf_resid_fun() experimental: Add Residual Lines from a Function to a Plot
gf_square_reduce() gf_squareduce() experimental: Add Squared Reduction Visualization to a Plot
gf_square_resid() gf_squaresid() experimental: Add Squared Residual Visualization to a Plot
gf_square_resid_fun() experimental: Add Squared Residual Visualization from a Function to a Plot
StatResid: Carry a prediction alongside the observation it belongs to
GeomResid: Draw a residual as a segment from a prediction to an observation
GeomSquareResid: Draw a residual as the square it would make

Evaluating models

Pull estimates out of fitted models (useful for bootstrapping), and quantify fit — including on separate train and test sets.

b0() b1() b() f() pre() p(): Extract estimates/statistics from a model
fit_stats() fitstats(): Test the fit of a model on a train and test set.
split_data(): Split data into train and test sets.

Plot theme and palettes

The colorblind-friendly ggplot2 theme that is applied when the package is loaded, and tools for customizing or toggling it.

coursekata_load_theme(): Utility function for loading all themes.
coursekata_palette(): The color palettes used in our theme system
coursekata_palette_provider(): Create a function that provides a colorblind palette.
coursekata_unload_theme(): Restore ggplot2 default settings
scale_discrete_coursekata(): A discrete color scale constructor with colorblind-safe palettes.
theme_coursekata(): A simple theme built on top of ggplot2::theme_bw

Package management

Install, update, and load the packages used in CourseKata courses.

coursekata coursekata-package: coursekata: CourseKata Statistics and Data Science
coursekata_attach(): Attach the CourseKata course packages
coursekata_install() coursekata_update(): Install or update all CourseKata packages.
coursekata_packages(): List all CourseKata course packages
coursekata_repos(): Get repositories for the packages.

Data

Data sets used in CourseKata courses and supplementary materials.

Ames: Ames, Iowa housing data
class_data: Generated "class data" for exploring pairwise tests
er: Emergency room canine therapy
fevdata: Forced Expiratory Volume (FEV) Data
Fingers: Data from introductory statistics students at a university.
FingersMessy: Raw data from introductory statistics students at a university.
game_data: Simulated math game data.
penguins: A modified form of the palmerpenguins::penguins data set.
Smallville: Simulated housing data
Survey: Students at a university were asked to enter a random number between 1-20 into a survey.
Tables: Tables data
tip_exp: Simulated data for an experiment about smiley faces and tips
TipExperiment: Data from an experiment about smiley faces and tips
World: Data on countries from the Happy Planet Index project.