Statistics can be defined as a branch of mathematics dealing with the collection, analysis, interpretation, and presentation of masses of numerical data. There are two basic kinds of data: measured data and counted data (often referred to as variable or attribute data). For us, only the concept of variation will be reviewed.

In the field of production and quality, no two things are ever exactly alike. That is one reason why we talk about machine and/or process specifications for example.

Recognizing that such variation exists in our products and processes, it is important to establish ways to measure variation, understand its causes and predict its occurrences. There are two types of variation: random and non-random. The random variation is often called the natural behavior of the process (experiencing chance or common causes of variability). Non-random (or unnatural) behavior is sometimes said to be caused by special or assignable causes.

A process, which can be viewed as a series of actions or operations, is influenced by several elements or factors, which contribute to the eventual outcome. These elements or causes of variation can be generally broken into the following typical categories or general sources of variation:

• Material
• Machine
• Method
• Manpower
• Measurement
• Environment

Each of these Elements contributes some degree of variability to the process. When a process is operating in random (natural) manner (with no special assignable causes present) it is said to be stable or in a state-of-control. Only when a process is stable can we draw meaningful conclusions and make valid predictions about its performance.