For the latest version of JMP Help, visit JMP.com/help.


Publication date: 05/05/2023

Explore Outliers

Find Outliers in Univariate and Multivariate Data

The Explore Outliers platform enables you to identify, explore, and manage outliers. Exploring and understanding outliers in your data is an important part of analysis. Outliers in data can be due to mistakes in data collection or reporting, measurement systems failure, the inclusion of error or missing value codes in the data set, or simply an unusual value. The presence of outliers can distort estimates and bias results toward those outliers.

Outliers inflate the sample variance. Sometimes retaining outliers in data is necessary, however, and removing them could underestimate the sample variance and bias the data in the opposite direction.

Whether you remove or retain outliers, it is a good practice to locate them. There are many ways to visually inspect for outliers. For example, box plots, histograms, and scatter plots can easily display these extreme values. See Visualize Your Data in Discovering JMP.

Figure 21.1 Multivariate k-Nearest Neighbor Outlier Example 

Multivariate k-Nearest Neighbor Outlier Example

Contents

Overview of Explore Outliers

Quantile Range Outliers
Robust Fit Outliers
Robust PCA Outliers
K Nearest Neighbor Outliers

Example of Explore Outliers

Launch the Explore Outliers Platform

The Explore Outliers Report

Quantile Range Outliers Report
Robust Fit Outliers Report
Robust PCA Outliers Report
K Nearest Neighbors Report

Explore Outliers Platform Options

Additional Example of the Explore Outliers Platform

Want more information? Have questions? Get answers in the JMP User Community (community.jmp.com).