Examining Standard Deviation - trillium_discovery - Latest

Trillium Discovery Center

Product type
Software
Portfolio
Verify
Product family
Trillium
Product
Trillium > Trillium Discovery
Version
Latest
Language
English
Product name
Trillium Discovery
Title
Trillium Discovery Center
Copyright
2024
First publish date
2008
Last updated
2024-10-18
Published on
2024-10-18T14:55:05.094442

Examining the results of standard deviation analysis gives you a general understanding of where your numeric attribute data falls in the range of deviation, and how much of your data is considered outlying.

Outliers and Mode Count

From standard deviations you drill down to view the corresponding outlier values. The higher the standard deviation level, the more outside the standard range of data the outlier is considered.

You can also examine mode count values. Mode counts are numbers that appear with the highest frequency in your dataset. For example, the mode value is 60 for the following set of data: 40 56 59 60 60 62 65 69 75 84.

You can view the values that are outliers and the data rows that contain the mode count values. You can also recode the values and export the rows as a .CSV file to be shared and imported into other applications.

Standard deviations

To examine standard deviations

  1. Open a data source.
  2. Click the Attribute Details tab.
  3. In the Attribute Name list, select the attribute that contains the standard deviations you want to examine. A tab named for the attribute opens below the Data Source: Name panel showing an overview of the attribute's metadata.
    Note: The attribute's predominant data type must be integers or decimals.
  4. Note the value in the Standard Deviation row. If the value is 1 or more, double-click the row. The Deviations: attribute_name tab opens and displays the following metadata columns:

    Column Name

    Description

    Deviation

    Deviation level number.

    Value Count

    Number of unique values in the attribute that have the deviation level number.

    Frequency

    Frequency of the values that have the deviation number; how many times the values occur in the attribute.

    Distribution %

    Percentage of rows in the attribute that match the deviation level. Distribution % shows distribution (in percents) of the deviation level across the attribute.

Outlier values

To view outlier values

  1. In the Deviations: attribute_name tab, double-click a row that contains the deviation level values you want to view. The Values: Selected Deviation tab opens.
  2. Examine the data values that match the deviation level you selected.

Mode counts, values, and data rows

To view mode counts, values, and data rows

  1. From the attribute's metadata tab, navigate to Mode Count and note the value.
  2. If the value is 1 or more, double-click the row. The Values: attribute_name tab opens, displaying mode counts in descending order by frequency. The row that contains the mode count with highest frequency is listed first. The Value column shows the data values that occur with the highest frequency in the attribute.
  3. (Optional) Recode data values. See Recoding Data Values.
  4. Double-click a row to open a Data Rows: Selected Value tab showing the data rows that contain the selected mode count value.
  5. (Optional) Export data rows. See Exporting Tab Rows.
    Note: The Mode Count and Mode Frequency values are also shown in a table in the Range section of a data source's Attribute Details tab.