Subscriber only lesson.
Sign up to this course to view this lesson.
About this lesson
Basic Graphical Analysis
When considering a distribution of data values for a process attribute, a graph of that data can be very insightful. The picture is often easier for team members to understand than a statistical description of the data distribution. This picture will often point the team to the process problem.
When to use
Graphical analysis is an excellent way to visualize patterns and key insights from data. Graphical analysis is also an excellent way to communicate data to the Lean Six Sigma team and stakeholders.
Graphical analysis creates a picture of the data which helps to put the data into context. It can display a great deal of data on one graph and the patterns in the data can reveal problems and correlation between process parameters and factors. Three graphs are often used because they are very easy to create.
Vertical Bar Chart
The vertical bar chart, also called a histogram, is an excellent technique with attribute data. The categories of the data are shown on the horizontal axis and are represented by columns on the chart. The vertical axis is the count of instances for the categories. This chart shows those categories with a significant count. A special case of this chart is the Pareto chart which orders the categories from largest to smallest.
The line graph is an excellent graphical display of variable data that is collected at fixed intervals. The fixed intervals are shown on the horizontal axis and the value of the data point is shown on the vertical axis. The data points are connected sequentially.
The line chart recognizes that there is a relationship between the data points. Patterns in the data, peaks, valleys or points of inflection are the significant elements of the graph. Those are the points where something unusual or special is happening in the process. A special case of the line graph is the Run Chart.
The scatter diagram shows the relationship between two factors that are both variable data parameters. When the pattern of the data is a line or ellipse that has an upward slope, there is a positive relationship. If there is a downward slope, there is a negative relationship. The more the ellipse collapses and approaches a straight line, the stronger the relationship. The closer the slope is to a 45° angle, the stronger the correlation.
If the pattern is totally random, or if the pattern is a horizontal line or vertical line, there is no relationship. One caution with scatter diagrams: Correlation does not mean causation. Both factors could be changing because of a different factor and not because of the changes occurring in the two factors that are plotted.
Hints & tips
- Make sure you understand whether the variation you see is due to special cause or common cause because the improvement strategy for each is totally different.
- Some people chase common cause variation as if it were special cause variation. This inevitably leads to tampering and often drives a stable process into a condition of instability.
Lesson notes are only available for subscribers.