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

Publication date: 09/28/2021

Explore Patterns Utility

Data can be messy, so it is sometimes hard to determine the validity of your data by visual inspection alone. The Explore Patterns utility is a tool for detecting unusual or unexpected patterns in your data. Although some patterns occur by chance or some innocent mechanism, they might indicate data that has been falsified or tampered with. This utility is most useful when the values are precise so that matches and patterns are less likely to happen by coincidence. The Explore Patterns utility is also designed to handle large data tables efficiently.

The Explore Patterns utility looks for duplicate values and duplicate sequences of values. These types of patterns can indicate data tampering strategies such as pasting the same value many times, pasting the same value across a range of cells, or copying a range of data and pasting it somewhere else. The utility also analyzes properties of the formatted values to determine whether the data are actual measurements or might have been generated by a random number generator. There are also options to examine distribution properties and detect linear relationships between columns across groups of rows.

Note: The Explore Patterns utility ignores excluded rows, but the results are not necessarily equivalent to if you had deleted the row. For runs of rows, such as the Longest Runs and Longest Duplicated Sequences options, an excluded row stops the run.

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