I would like to know the actual difference between UCL and USL. What is know is:-

USL- Upper standard limit specified by the customer

LSL- Lower standard limit specified by the customer

Example- Customer has specified that all shirt size of 42 cm can have a +-.5 variation. So USL is 42.5 and LSL is 41.5

These two are always specified by the customer and you don't have control over it.

UCL-Upper control limit which you get from your process

LCL- Lower control limit which you get from your process

Example- You are required to produce a shirt of 42 size. You at times may end up producing 44 sized shirt while manufacturing 42 size shirt -so 44 is your UCL. Similarly the minimum size you produce while manufacturing 42 sized shirt is say 40 instead of 42- so 42 is your LCL. Is this a correct assumption??

Now to give you a real time scenario:-

We conduct mystery shoppers at our test centers across India to see if the centers are adhering to the required quality and security standards. They fill up a specific questionnaire and report back performance to us. Often the shoppers may find test center closed or unable to conduct exam due to technical issue, Lack of knowledge, new test administrator, test administrator not available and many other issues. Such issues results in failed shop and the vendor company charges us 75% of the shop fee (as they have spend man-hours in recruiting, training and sending the shopper to the site). So in short every failed shop is a potential shop loss. I have data for the last 12 months of failed shop However the customer is not bothered about failed shop (as they are more concerned with the final shop numbers). So we don't have USL and LSL. So would UCL would be the maximum failed shop on any given month? And LCL the minimum failed shop on any given month? Please confirm if this assumption is correct. And then find the mean and standard deviation and then the sigma level at which my process is currently working?

Based on VOB (every failed shop is a potential shop loss) and COPQ (rework on retraining these sites or taking these sites of the list) I would want to bring this failed shop % from 5% to 1% (this is internal specification). So now my USL is 1%. What is my LSL then? So how do I proceed now towards finding my mean and standard deviation? Does the mean still remain the same as before?

I really need help on this as it seems like I am missing something, somewhere.

Dear Anis,

Natural process limits are known by several names in the literature: natural process variation, normal process variation, and natural tolerance. In all cases, these terms refer to the +-3σ limits (that is, 6σ spread) around a process average. Such limits include 99.73% of the process variation and are said to be the "voice of the process."

Hope this will clarify your doubt on control limits. Secondly your as-is process failure is 5% and you want your process to be targeted at USL 1%, here you can consider LSL as 0% . Your process mean and standard deviation will not change because of change in specification limit.

Regards,

Sujeet