Learn R Programming

nullabor: lineup and Rorschach plots for visual inference

Di Cook, Hadley Wickham, Niladri Roy Chowdhury, Heike Hofmann, Mans Thulin November 29, 2024

nullabor

Tools for graphical inference: prevent fooling yourself with the Rorschach protocol and check the surprising features in your data with the lineup protocol!

Installation

The nullabor package can be installed from CRAN

install.packages("nullabor")

You can install the development version of nullabor from github with:

# install.packages("devtools")
devtools::install_github("dicook/nullabor")

Copy Link

Version

Install

install.packages('nullabor')

Monthly Downloads

3,113

Version

0.3.16

License

GPL (>= 2)

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/dicook/nullabor

Maintainer

Di Cook

Last Published

September 26th, 2026

Functions in nullabor (0.3.16)

P-value calculations.

Distance based on separation of clusters

Rotation residuals.

A theme to minimally strip away the context

Distance based on the regression parameters

Sample size calculator

Residuals simulated by a normal model, with specified sigma

Generate null data by permuting a variable.

The Rorschach protocol.

Sample turk results

Distance for univariate data

Bootstrap residuals.

Parametric bootstrap residuals.

Power calculations.

Los Angeles Lakers play-by-play data.

Generate null data by simulating from a time series model.

Wasp gene expression data.

Finds the number of bins in x and y direction which gives the maximum binned distance.

Add true data into data frame containing null data sets.

Distance based on side by side Boxplots

Use decrypt to reveal the position of the real data.

Calculating the difference between true plot and the null plot with the maximum distance.

Binned Distance

Plotting the distribution of the distance measure

Polls and election results from the 2012 US Election

Empirical distribution of the distance

Conversion rate of 1 Australian Doller (AUD) to 1 US Dollar

Calculating the mean distances of each plot in the lineup.

Generate null data with null residuals from a model.

The line-up protocol.

Generate null data with a specific distribution.

Check distributional assumptions using Q-Q plots and the lineup protocol.

lineup_residuals

Compare residual plots of a fitted model to plots of null residuals.

Computing th distance for the null plots

Find plot data. If data is not specified, this function will attempt to find the data corresponding to the last ggplot2 created or displayed. This will work in most situations where you are creating the plot and immediately displaying it, but may not work in other situations. In those cases, please specify the data explicitly.

lineup_histograms

Check distributional assumptions using histograms and the lineup protocol.

Permutation residuals.