Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

A histogram is a summary chart that displays a count of data points falling in various ranges. The effect is a rough approximation of the frequency distribution of the specified measurement data. In SPC analysis, histograms are often used in combination with control charts to dig into variations and determine whether processes are in control or out of specification. This data can reveal important information and opportunities across one manufacturing line, one site, or even across multiple sites. More information: Histogram (Wikipedia.org)Example histogramImage Removed


Example histogramImage Added


A histogram frequency bar chart shows an approximate representation of the spread or distribution of numerical or categorical data: 

  • The Nominal value is the user-defined target value of a process.

  • The Mean or Average value is the average of the data points used to calculate the process center line. 

  • The Lower Specification Limit (LSL) and Upper Specification Limit (USL) determine how well a process delivers on customer requirements. Specification limits are derived from the customer requirements and specify the minimum (LSL) and maximum (USL) acceptable limits of a process.

  • Cp is a process capability index that is a ratio of the specification range (USL-LSL) to the standard deviation of the process.

  •  Cpk is a process capability index used to measure the minimum of the Cpl and Cpu statistics. Cpk indicates whether or not the process being analyzed is capable of producing few or no defects (the higher the number, the less likely it will be that defects are produced) within a customer's specification limits.

  • The CpU statistic is relates the difference between the USL and the center line to the standard deviation.

  • The CpL statistic relates the difference between the center line and the LSL to the standard deviation.

Use the SPC Measurements​ data source to create a histogram

You use the SPC Measurements data source in DataMiner to create histogram frequency bar charts. Measurements include a variety of data collection activities specified in the NPI Process Definition window.

  1. Select the SPC data source on the left side of the window, then select the SPC Measurements data source under Data Sources.

  2. To view and select measurements for a histogram, select the Options tab, select the Measurements button, enter an asterisk * in the Lookup window, then press Enter.

  3. Under Histogram Options, Specify the Bin Count.

  4. (Optional) To use a sample population for the histogram, select the Using a Sample Population check box.

  5. Under User-Defined Specification Limits, do the following:

    • Select the Upper Specification Limit check box, then enter the upper limit for this histogram.

    • Select the Lower Specification Limit check box, then enter the lower limit for this histogram.

    • Select the Nominal Value check box, then enter the desired nominal value for the histogram.

  6. iconfalsetitle

    Use the other tabs in the DataMiner window to specify additional settings for the histogram, then select the Execute button to generate the histogram. 

    Note


Note

:

For more information about using the Analytics client application to create data workbooks, reports, and charts, see Using Analytics.

Image Removed


SPC Measurements Look Up dialogImage Added

What's the difference between a bar chart and a histogram?

The most significant difference between a bar chart and a histogram is that a histogram is only used to plot the frequency distribution of the specified measurement data in a continuous data set that is divided into a group or class of data points or intervals called data bins. Each bar on a histogram represents a data bin. Bar charts can be used for a many other types of variables—including ordinal and nominal data sets. 

Unlike a bar chart, there are no gaps between the bars in a histogram (however some bars might be absent, reflecting no frequencies). This is because a histogram represents a continuous data set, and as such, there are no gaps in the data (although you will have to decide whether you round up or round down scores on the boundaries of the bins).