An important aspect of SPC chart is organizing the data collection into subgroups. Each subgroup must be in control. Data points are either averages of subgroup measurements or individual measurements plotted on the Label and Value columns.

Data must be collected randomly at a determined frequency. You must construct rational subgroups wherein the variations must be between subgroups rather than within subgroups. From the subgroups (subsets), the following can be calculated for each subset:

The sample is a collection of observations used to analyze a system. As the subgroup size increases, the standard deviation of the distribution of averages decreases. If the subgroup size is not large enough, process shifts go undetected. If the subgroup size is too large, there is a possibility of insignificant processes.

For Variable Control charts, all the data in the subgroup has a common data, such as data on a particular date, single shift. For Attribute Control charts, a subgroup is the group of units that were inspected to obtain the number of defects or the number of rejects. c and u charts displays the number of defects whereas p and np charts displays the number of rejects.