Picking up where we left off, the components of the control chart include a center line, an upper and control control limits. Quality characteristic values are plotted along the vertical axis. There are two types of control charts, attribute and variable. With control charting we can know when to take corrective action, the type of remedial action to take, when to lead the process along, the process capability, and the possible avenues for quality improvement. Before we can eliminate variation, we must recognize that there are really two types of variation at play. Special cause is assignable variation, something that is not inherent in the process. Common cause is due to chance. Variability due to common or chance causes is something inherent in the process. Demming believed that 15 percent of all problems are due to special causes. Action on the part of management and workers can reduce special causes. Demming also believed that about 85 percent of all problems are due to common causes. These can only be solved by management since you must change the system. The center line is where the average or target value will reside. Typical processes can be deemed out of control when points are outside the control limits, there are nonrandom patterns, or if target values are on only one side of the center line. If the process is under statistical control then we can estimate the process parameters, the mean, the standard deviation, and the process capability. Per the central limit there, as we increase the sample size, the control limits will be drawn closer together. This is due to a decrease in the variance. Control limits are usually placed at plus or minus three sigma. This captures 99.74 percent of the behavior of the sample statistic. This is our indicator that the process is in control and our process consistently performs within these limits. In most cases sampling is done in time order or by process. We call this type of sampling the instant of time method. Observations are selected at approximately the same time for the population under consideration. If we want to detect a small shift, a large sample size is needed. Choosing large samples frequently provides the most information but is not always feasible. We must consider whether we have destructive testing and the cost of sampling. Once you have localized and eliminated assignable causes we should remove out of control points and revise the center line and control limits. There is no need to maintain control charts if the process demonstrates consistent capability. Instead, focus your attention and resources on other areas. Be aware that the control limits on a control chart are influenced by the variability in the process. As such, these control limits will change. Today's technology makes this a very manageable behavior. Control charts are easy to set but very difficult to maintain. Often our failure to maintain comes down to our inattention, in other words, failing to make adjustments when the control chart detects an issue. Prioritization of productivity also overshadows control charting. Lack of training can also derail a control charting program