Histograms provide a graphic summary of variations in a set of data. This is done by partitioning the range of data into several intervals of equal length, counting the number of points in each interval, and plotting the counts as bar lengths. Histograms are useful in the study of process capability since they graphically display one or more of three important data distribution properties: shape, location, and scatter.
The process should be, approximately, normally distributed for the SPC techniques, supported by Oracle Quality, to be directly applicable. If the process is not normally distributed, data should be transformed to make them approximately normal, before these techniques can be applied.
Histogram analysis is a basic step in analyzing a process and can provide the following sense of accomplishment:
We have quantified some aspect of the process; we are managing by facts, not opinions.
We have a better understanding of the variability inherent in the process; we have a more realistic view of the ability of the process to produce acceptable results consistently.
We have new ideas and theories about how the process operates or about the causes of a problem and we have set the stage for additional investigative efforts.
We have pictured the distribution of the process.
You can graphically display, in histogram form, quality results for any collection plan element with a numeric data type. You can select and graph a subset quality results values.
You can create histograms from "scratch" or you can create them by copying settings from another chart, descriptive statistic view, or custom report. Copying settings allows you to view the same subset of data in different ways. See: Copy Settings.
You can save your chart settings. You can re-create charts using these saved settings, and you can change these settings to create new charts.
The X-axis of the chart (the horizontal dimension) represents the value of the selected collection plan element. The Y-axis of the chart (the vertical dimension) represents the count or sum of occurrences of the primary collection element on the X-axis. Usually, this axis represents a quantity or count of occurrences. For example, if you select the collection plan element Quantity Defective, the Y-axis is used to show the frequency of occurrences.
Optionally, define specifications and specification elements with specification limits. See: Defining Specifications and Defining Specification Elements.
Navigate to the Histograms window.
Choose the Copy Settings button. See: Copying Settings.
Enter missing information or change the copied information as required (see below). (You can change all copied settings except the collection plan.)
Navigate to the Histograms window.
Enter the Chart Name.
To save your chart parameters, you must enter a chart name.
Select the Collection Plan.
If you are creating a chart, you can select any collection plan, even those that are no longer effective. If you are changing a chart, you cannot change the collection plan.
Enter the Chart Title.
The text you enter here is displayed at the top of the chart.
Enter the chart Description.
The text you enter here is displayed at the top of the chart, under the chart title.
Select the Collection Element.
You can select any collection element on the collection plan, however, you must select a collection plan element with a numeric data type.
Optionally, select or find the specification.
You can only select specifications that have specification elements in common with the selected collection plan element defined. See: Defining Specification Element.
You can find and select any specification, even specifications that do not have the selected collection element as a specification element. If this is the case, Upper and Lower Specification Limits and the Target Value are defaulted from the collection element. See: Defining Collection Element Specification Limits.
Optionally, enter the Number of Bars for the graph.
If you do not enter a number, the number of bars is calculated as the square root of the number of points.
Optionally, enter the Number of Points.
The Number of Points represents the total number of data points to be included. If you do not enter a specific number of points, all points are used. If you do enter a specific number, the most recently collected results are used.
Navigate to the Show Results Where region of the Control Chart window. See: Finding Quality Results.
If you do not select which quality results to chart, all results associated with the collection plan are used.
Choose the View Chart button. The histogram you created will be displayed in a separate window.
Choose the Save Settings button if you want to save the inquiry settings.
Choose Export Results from the Tools menu. See: Exporting Quality Results.