<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />The question below was eventually sent to JMP Support.
The following question arose during the SPC training we recently held: We used the attached data and the process capability platform as in the included script (spec limits are in the data). The plot suggests some potential issues, but there are no real issues in the data (not for 1 and not even for a threshold of 1.33). Consulting the JMP help increased the confusion:
By default, the Ppk slider and number edit box are set to Ppk = 1. This approximates a non-conformance rate of 0.0027, if the distribution is normal. The goal triangle represents the Ppk shown in the edit box. To change the Ppk value, move the slider or enter a number in the edit box.
When you select Shade Levels from the Goal Plot red triangle menu, shaded areas appear within the goal plot triangle. See Goal Plot. The shaded areas are described as follows, with p representing the value shown in the Ppk edit box:
| • | Points in the red area have Ppk < p. |
• | Points in the yellow area have p < Ppk < 2p. |
| • | Points in the green area have 2p < Ppk. |
So from that I get that the green area has those points that have Ppk > 2 (2*threshold), yellow between 1 and 2, and red for Ppk below 1. The smallest Ppk is about 1.6 (cf. sorted table), and only 6 are below 2. Yet, there are several points in the red area, and plenty in the yellow. So this doesn’t seem to match up with what’s written in the help relative to what we get. We observe this issue in both JMP 12.1 and in Bea’s EA Version 13. Interestingly, one participant tried JMP 11 and it looked different and more reasonable there.
We realised that the variables that seem to be indicating capability issue were rather identifiable by low Cpm values. But that was not entirely true for all points in the red area.
So the question: Are we missing something? Has there been a change from JMP 11 to 12 that explains this?
Cheers,
Bea Blum and Michael Meyners
Here is the answer we got from JMP Support:
| Beatrice, Thank you for contacting JMP Technical Support. I am sorry the documentation on the Goal Plot is not as clear as it could be. The description of the red, yellow, and green areas is accurate if the target is centered between the two spec limits. In many of the cases for this data, the target is not at the center point. Since the goal plot makes use of the target value, and in some of these cases the observed values are not centered on the target, the point moves out of the area where we would expect to see it based on the Ppk. The placement of the points probably more accurately reflects the Cpm, rather than the Cpk or Ppk. Take, for example, X_25. While the Ppk in this instance is 2.081, only the upper most observed values are close to the target. There are no out of spec values, but the process is not centered on the target. The Cpm in this case is only 0.309. I hope this information is helpful. Please let me know if you have additional questions or need further clarification. I will be happy to continue working with you should you have any follow-up questions regarding this matter. The track will remain open for an additional 7 days to allow you an opportunity to request further assistance on this issue. I encourage you to respond to let me know if I have resolved this issue to your satisfaction. Thanks for using JMP! Sue Walsh JMP Technical Support Statistician |
