Publication date: 08/13/2020

Explore Patterns Utility Options

The control panel and Explore Patterns red triangle menu contain options for summary and pattern tables. The tables and their contents are as follows:

Most Duplicated Values

Shows or hides a table of the values that appear most frequently in the data. Shows up to ten numbers for each column.

Longest Runs

Shows or hides a table of the longest run of the same value. The table contains the following information:

Starting Row

The row number that corresponds to the start of the run.

Count

The length of the run.

Value

The value of the entries in the run.

Rarity

A measurement of how rare it would be for the run to occur by chance. A high rarity indicates that it is not likely that the run occurred by chance. See Rarity in Longest Runs.

Longest Duplicated Sequences

Shows or hides a table of the longest sequence of values that appears more than once in the same column. Sequences of repeated values are also considered. If a sequence is duplicated more than once, each instance appears in the table. The table contains the following information:

Starting Row I

The row number that corresponds to the start of the first sequence.

Starting Row J

The row number that corresponds to the start of the duplicate sequence.

Count

The length of the sequence.

Rarity

A measurement of how rare it would be for the duplicate sequence to occur by chance. A high rarity indicates that it is not likely that the duplicate sequence occurred by chance. See Rarity in Longest Sequences.

First few values

The first few values of the duplicate sequence. Shows up to three values for each sequence.

Formatted Widths

Shows or hides a table of overall widths and decimal widths of the formatted values. The table contains the following information:

Width

The width size.

Overall Count

The number of observations in the column whose overall width equals the specified width.

Decimal Count

The number of observations in the column whose decimal width equals the specified width.

Fraction Length

Shows or hides a table of the continued fraction lengths for the values. A continued fraction is a representation of a number as a sequence of continually divided terms. The fraction length can indicate how rational a number is. Lengths of 15 or more indicate that the number is an irrational number, such as from a root function, a function involving an irrational number, or from a random number generator (Benford, 1938).

Note: In Explore Patterns, the maximum fraction length is 15. Numbers with fraction lengths of 15 or more are all reported as 15.

Length

The length of the continued fraction.

Count

The number of observations in the column whose continued fraction length equals the specified continued fraction length.

Leading and Trailing Digits

Shows or hides a table of counts for each leading and trailing digit, 1 through 9. There is also an expected rate column for the leading digits that is based on Benford’s Law. Benford’s Law states that the frequency that a number has a first digit that is equal to a is Fa = log10(a+1/a). This law applies to data that have a large range of numbers that all have four or more digits.

Spec Limit Matches

(Available when at least one of the columns has a Spec Limit column property.) Shows or hides a table of values that are exactly the lower specification limit, upper specification limit, or target value. If there are no exact matches, the report is not shown.

Distribution wrt Spec Limits

(Available when at least one of the columns has a Spec Limit column property.) Shows or hides a table of observed versus expected observations that are outside of the specification limits.

Duplicates Across Columns

Shows or hides the Duplicates Across Columns report. The report contains a table of sequences of values that appear in the same rows across more than one column. There is a note at the top of the report that states the minimum length of a sequence for it to be considered a duplicate. This number is specified in the launch window or control panel as Minimum Cross Column Duplicate Run Size. There is also a Colorize option at the top of the report. See Colorize Duplicates Across Columns.

Colorize Duplicates Across Columns

(Available only after Duplicates Across Columns has been selected.) Colors cells in the data table to correspond to the duplicate matches found in the Duplicates Across Columns report. The rows that contain the duplicates are also selected.

Linear Relationships

Shows or hides the Linear relationships between variables report. The report contains a table of exact linear relationships across columns over a specified number of sequential rows. An exact linear relationship is defined as a linear relationship that has an R2 value greater than or equal to 0.999999. There is a note at the top of the report that states the minimum number of rows considered. This number is specified in the launch window or control panel as Minimum Rows for Linear Relationships. There is also a Colorize option at the top of the report. See Colorize Linear Relationships.

Colorize Linear Relationships

(Available only after Linear Relationships has been selected.) Colors cells in the data table to correspond to the linear relationships found in the Linear relationships between variables table. The rows that contain the linear relationships are also selected.

Save Columns

Contains the following save options:

Save Table of Runs

Saves the longest runs for all columns to a new data table. The data table contains the same columns as the Longest Runs table in the Univariate Patterns report and is sorted by Starting Row.

Save Table of Duplicate Sequences

Saves the longest duplicate sequences for all columns to a new data table. The data table contains the same columns as the Longest Duplicate Sequences table in the Univariate Patterns report and is sorted by Starting Row I.

Save Duplicates Across Columns

Saves the Duplicates Across Columns table to a new data table.

Save Linear Relationships

Saves the Linear relationships between values table to a new data table.

Ordering Columns

Contains options for ordering. When you change the ordering, the column list in the Univariate Patterns report is reordered. The top column is automatically selected and the report for only that column is displayed. The ordering options are as follows:

Order by Runs Rarity

Orders the column list by the rarity values of the longest runs. Higher rarity values are at the top.

Order by Sequence Rarity

Orders the column list by the rarity values of the long duplicate sequences. Higher rarity values are at the top.

Order by Column Name

Orders the column list in alphabetical order by column name.

Original Order

Orders the column list in the original order in which the columns were specified in the launch window.

Clear Cell Colors

Clears the cell colors for columns selected in the data table or for all columns if no columns are selected in the data table.

See Redo Menus and Save Script Menus in Using JMP for more information about the following options:

Redo

Contains options that enable you to repeat or relaunch the analysis. In platforms that support the feature, the Automatic Recalc option immediately reflects the changes that you make to the data table in the corresponding report window.

Save Script

Contains options that enable you to save a script that reproduces the report to several destinations.

Save By-Group Script

Contains options that enable you to save a script that reproduces the platform report for all levels of a By variable to several destinations. Available only when a By variable is specified in the launch window.

Univariate Patterns Report Options

Each Univariate Patterns red triangle menu contains the following options:

Select Most Duplicated

Selects the observations in the data table that correspond to the values in the Most Duplicated Values table.

Select Longest Runs

Selects the observations in the data table that correspond to the values in the Longest Runs table.

Select Longest Duplicate Sequences

Selects the observations in the data table that correspond to the values in the Longest Duplicate Sequences table.

Select by Formatted Width

Selects the observations in the data table that correspond to the values in the Formatted Widths table that have the user-specified overall width.

Select by Decimal Width

Selects the observations in the data table that correspond to the values in the Formatted Widths that have the user-specified decimal width.

Select by Fraction Length

Selects the observations in the data table that correspond to the values in the Fraction Length table that have the user-specified fraction length.

Select by Leading Digit

Selects the observations in the data table that correspond to the values in the Leading and Trailing Digits table that have the user-specified leading digit.

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