Discrete data are only a finite number of values possible or if there is a space on the number line between two possible values. For example, it’s impossible to roll the 2.3 on a roll of the dice. You can either roll a two or three but nothing in between. One type of discrete data, sometimes referred to as attribute data are two-state (binary). This ‘attribute data’ might be pass/fail, good/bad, the color matches/the color doesn’t match, etc.
Use: Attribute data is used to monitor processes exhibiting four conditions, and as such there are four different names for these charts (c chart, u chart, np chart, and p chart). We maintain throughout the course that one should strive for continuous data because that gives the team an idea of the magnitude of a problem compared to just finding out whether the process’ result is good or bad. Sometimes the team doesn’t have a choice, so the team is faced with either converting attribute data into variable-discrete data (e.g., Likert scale), or the team looks up-stream in the process to strive to find continuous data to prevent a defect.
