| Run Charts | | | | pitches are going to be where he wants them. There |
| Run charts (often known as line graphs outside the | | | | will be some variation, but not too much. If he is "wild", |
| quality management field) display process | | | | his pitches aren't going where he wants them; there's |
| performance over time. Upward and downward | | | | more variation. There may not be any special causes - |
| trends, cycles, and large aberrations may be spotted | | | | no wind, no change in the ball - just more "common |
| and investigated further. In a run chart, events, shown | | | | cause" variation. The result: more walks are issued, |
| on the y axis, are graphed against a time period on the | | | | and there are unintended pitches over the plate where |
| x axis. For example, a run chart in a hospital might plot | | | | batters can hit them. In baseball, control wins ballgames. |
| the number of patient transfer delays against the time | | | | Likewise, in most processes, reducing common cause |
| of day or day of the week. | | | | variation saves money. |
| | | | Happily, there are easy-to-use charts which make it |
| Control Charts | | | | easy see both special and common cause variation in |
| Every process varies. If you write your name ten | | | | a process. They are called control charts, or |
| times, your signatures will all be similar, but no two | | | | sometimes Shewhart charts, after their inventor, |
| signatures will be exactly alike. There is an inherent | | | | Walter Shewhart, of Bell Labs. There are many |
| variation, but it varies between predictable limits. If, as | | | | different subspecies of control charts which can be |
| you are signing your name, someone bumps your | | | | applied to the different types of process data which |
| elbow, you get an unusual variation due to what is | | | | are typically available. |
| called a "special cause". If you are cutting diamonds, | | | | All control charts have three basic components: |
| and someone bumps your elbow, the special cause | | | | - A centerline, usually the mathematical average of all |
| can be expensive. For many processes, it is important | | | | the samples plotted. |
| to notice special causes of variation as soon as they | | | | - Upper and lower statistical control limits that define |
| occur. | | | | the constraints of common cause variations. |
| There's also "common cause" variation. Consider a | | | | - Performance data plotted over time. |
| baseball pitcher. If he has good control, most of his | | | | |