Anscombes quartet
Anscombe's quartet consists of four datasets, each containing a series of [x, y] point pairs. Although they share almost identical simple statistical properties, their graphical representations differ dramatically. The datasets illustrate why graphical data exploration should precede statistical analysis and demonstrate the effect of outliers on statistical characteristics.
Dataset description and usage context
Dataset Overview
Dataset Name
Anscombe's Quartet
Dataset Description
Anscombe's quartet is a collection of four datasets that have nearly identical simple statistical properties but exhibit markedly different graphical behavior. Created by Francis Anscombe, the collection highlights the importance of graphical data exploration before statistical analysis and shows how outliers can affect statistical characteristics.
Dataset Structure
- Contains 4 independent datasets.
- Each dataset is an array of
[x, y]tuples.
Dataset Example
[
[
[10,8.04],
[8,6.95],
...
],
[
[10,9.14],
[8,8.14],
...
],
...
]
Dataset Usage Example
var data = require( datasets-anscombes-quartet );
// Example code demonstrates how to convert the dataset into a matrix and compute mean and variance for each group.
Installation and Use
- Installation command:
npm install datasets-anscombes-quartet - Usage example:
var data = require( datasets-anscombes-quartet );
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.