Cpk for small sample sizes?Hi everyone,
I have a JMP user making coils, which are then shipped to different customers. They measure the thickness of each coil, and then take out a bunch to complete an order. The customer receives the Cpk for their particular bunch of coils. The issue is that there may be very few coils per order, rendering the Cpk essentially meaningless. Does it make more sense to send the customers the Cpk calculated from all coils made that week, or is there a more appropriate statistic they should use? Any help with this would be appreciated.
Re: Cpk for small sample sizes?I’d actually stay out of the fray on this one… it dances really close to the “consulting” line. One thing I would tell them is that they could do a power and sample size calculation on Cpk and decide what to do based on that.
Two of my favorite books on this subject are “Sample Size Calculations: Practical Methods for Engineers and Scientists” by Mathews and “Sample Size Determination and Power” by Ryan. Both have equations that could be coded up in a column formula to make an adhoc calculator.
Best,
MRe: Cpk for small sample sizes?Hadley, I agree with Mike and Phil on avoiding consulting. I tend to fall into that trap myself.
With that said... and just to add to the conversation... can I interpret your original note as "100% inspection of all coils?" If so, I don't know why they would need CpK at all, since CpK is a statistical estimate based on a small sample from a large lot. Why not just supply the measured info on each coil shipped, and be done with it?
Re: Cpk for small sample sizes?Good point, @JerryFish .
What they are doing is just very weird and I don't understand why they are doing it. I've never heard of a manufacturer stating the CpK for a batch of items to their customer. I can understand why a customer might want to know the CpK for the process - to have some assurance that the supplier has control over quality.
