Same Stats, Different Graphs

2017/05/02 by Justin Matejka, George Fitzmaurice · 1 voice · 10 citations
Agricultural and Biological Sciences · Computer Science · #Data Management and Algorithms #Data Visualization and Analytics #Sensory Analysis and Statistical Methods

paper · doi:10.1145/3025453.3025912

openalex publication_date 2017/05/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Datasets which are identical over a number of statistical properties, yet produce dissimilar graphs, are frequently used to illustrate the importance of graphical representations when exploring data. This paper presents a novel method for generating such datasets, along with several examples. Our technique varies from previous approaches in that new datasets are iteratively generated from a seed dataset through random perturbations of individual data points, and can be directed towards a desired outcome through a simulated annealing optimization strategy. Our method has the benefit of being agnostic to the particular statistical properties that are to remain constant between the datasets, and allows for control over the graphical appearance of resulting output.

Cited by

• Uninterpretable graphs at a scientific conference
• Teru Teru Bōzu: Defensive Raincloud Plots
• Data Understanding Survey: Pursuing Improved Dataset Characterization Via Tensor-based Methods
• Informative data visualization with raincloud plots in JASP
• Graphs in phylogenetic comparative analysis: Anscombe's quartet revisited
• The Landscape of College-Level Data Visualization Courses, and the Benefits of Incorporating Statistical Thinking
• Same Stats, Different Graphs (Graph Statistics and Why We Need Graph Drawings)
• Same Quality Metrics, Different Graph Drawings
• Reframing Pattern: A Comprehensive Approach to a Composite Visual Variable
• Beyond Scores: Proximal Diffusion Models

Discussions

• the datasaurus dozen, which is the original quartet on steroids Matejka, Justin, and George Fitzmaurice. “Same Stats, Different Graphs: Generating Datasets with Varied Appearance and Identical Statis [bsky, 7 points, 1 comments]

Related

• Same Stats, Different Graphs (Graph Statistics and Why We Need Graph Drawings)
• Guided Graph Generation: Evaluation of Graph Generators in Terms of Network Statistics, and a New Algorithm
• Analysis of data in the form of graphs
• Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation
• The Multiple Random Dot Product Graph Model