Histogram & capability analysis

In the last post we looked at tools for analyzing distribution of variable data. Histogram is the most popular distribution analysis tool. Using the histogram we can also predict the capability of the process.

Histogram shows the frequency distribution of the data. The curve shows shape of the distribution. Skew measures asymmetry of the distribution. A positive skew indicates a histogram with a longer right side tail whereas a negative skew has a longer left side tail.

So where is the tie in between the histogram and capability analysis?
Process capability analysis compares process performance against specifications. Histogram shows the distribution of process data. If the histogram graphically showed the specification limits then it is showing if the process is performing within specs or not. So visually the histogram would show if the process is producing good parts or not.

Numerically capability of a process can be analyzed by calculating the capability indices. There are several capability indices each showing an aspect of process capability. Most popular capability indices are Cp, Cpk, Pp, Ppk.

Read our White Paper on different capability indices and their uses.

What capability indices do you to determine process capability? How do you use the histogram for distribution analysis?

Distribution Analysis for variables

Distribution analysis for variable data is one of the critical analysis that help us understand how much
variation exists in the data. This in turn helps us understand how wide the process is and whether it falls within the specification limits.

There are several tools for studying distribution of variable data. The tools listed below are some of the popular ones:
1. Histogram
2. Stem and Leaf plot
3. Dot plot
4. Box plot

Histogram being the most popular to understand the nature of distribution of variable data. Dot and Stem & Leaf plot are more detailed versions for analyzing data distribution.
Box plots (also known as Box and Whisker plot) are used to compare distributions. Example for using a box plot would be to compare machine performance.

The figure below shows a comparison of the 4 tools.

We would love to hear which of the above tools have you used for analyzing distribution of variable data. Write to us at info@sybeq.com

Analytical tools for variable, attribute data

We have looked in the data analysis piece of Lean Six Sigma projects.
By now we know that data analysis is key in a Lean Six Sigma project. At the same time it is equally important to avoid analysis paralysis. A Green or Black Belt must know that there are different analytical tools for the type of data.

There are 2 data types
1. Variable or Continuous : Data that is measured and readings can have decimals. Eg. Weight, length, diameter. 3.56lbs, 4.5mm
2. Attribute or Discrete: Data that is counted and readings are integers. Eg. number of rejects, number or cracks

In attributes, there are 2 categories specific to the type of count.
Attribute types:
1. Defectives - The number of parts that are rejected are defectives. Also called non conforming units.
2. Defects - Number of specific problems with parts eg. burred, cracked, scratched parts. Defects could be fixed by repairing them. These parts are called non conformities.

For every data type there is a set of analytical tools. The figure below shows the commonly used tools by the type of data.

Is my data variable or attribute?

From my training class last week, I had an interesting question from one of my class students who was from the healthcare industry.

The student asked "I measure success of tests conducted by lab personnel. For example, I monitor number of blood tests were conducted every day by each lab assistant. I also monitor how many attempts were required for the assistant to successfully draw blood and complete the test.
I want to plot an SPC chart for the number of successful blood draws in single attempt. Should I use variable or attribute control charts?"

My answer to her was a series of questions..
Question 1: What do want the SPC chart to tell you?
Answer : Number of successful blood draws in single attempt.
Also, success rate of each lab personnel.

Question 2: Are either of the above measurements or counts?
Answer : They are counts.

Question 3: What SPC chart helps chart count data?
Answer: Attribute control charts

My student was able to answer her own question after breaking down her problem in small sections.

Have you struggled with data types?
Do you have questions about type of SPC charts you should use?
Please visit our tutorial on "SPC in healthcare" at www.sybeq.com/Tutorial.aspx