Process
Six Sigma – iSixSigma › Forums › Old Forums › General › Process
- This topic has 5 replies, 5 voices, and was last updated 17 years, 10 months ago by
TO.
-
AuthorPosts
-
October 11, 2004 at 1:31 pm #37181
tressey thompsonMember@tressey-thompsonInclude @tressey-thompson in your post and this person will
be notified via email.In characterising a process, data shows that the target value is equal to the mean. In this case which of the follwoing would by defininition be a correct statement?
1. The target is centered between USL and LSL
2. The mean is centered between the control limits
3. There is only one specification limit
4. the process has a small spread
5. the process is centered.0October 11, 2004 at 2:12 pm #108861
aBBinMNParticipant@aBBinMNInclude @aBBinMN in your post and this person will
be notified via email.None of the above.
If we stipulate that the process is normally distributed, 2 would be true. We have no info regarding specs, so 1 and 3 are out. We have no info regarding variance, so 4 is out.
One could argue that a process is centered around (or upon) itself, but one would generally assume that “centered” means “centered between USL and LSL” or “centered on target.” However, because we don’t know if the process is normal or not, we can’t assume that mean is the most appropriate measure of central tendency.0October 11, 2004 at 2:42 pm #108863Also, a target isn’t always the center of a control limit or spec. limit. (For example, a parallelism or perpendicularity callout, where the target is usually zero).
0October 11, 2004 at 3:03 pm #108865
tressey thompsonMember@tressey-thompsonInclude @tressey-thompson in your post and this person will
be notified via email.thanks. My question did state that the target and the mean were equal. I have no other information just what I provided initialy. I therefore assumed that number 1 was correct but then thought number 2 could easily be correct, and so wanted to know what others thought.
0October 11, 2004 at 3:57 pm #108874
KBaileyParticipant@KBaileyInclude @KBailey in your post and this person will
be notified via email.You could probably assume 5 is correct. One way to define “centered” is that the process mean equals the target.
The trouble is that some testers would actually use such poorly-written questions and expect you to read their minds. I’m with aBBinMN that you shouldn’t assume mean to be the only/best measure of central tendency, especially given the way the question was worded.
(If the question was intended as a measurement system, I’m predicting it to be a poor one.)0October 14, 2004 at 3:55 am #109061If the target is equal to the mean the process is centered. From a process standpoint, the process is on target so you don’t have to focus on moving the process average. However, the opportunity may be reducing the spread or standard deviation of the process.
0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.