- September 16, 2018 at 1:09 pm #56095
Hi – request guidance on 3 key questions around sampling
1) confidence level – 95 vs 98 – am in the outsourcing world where the client performs a certain number of external audits in invoices we process, while I have been pushing for 98 CL, the client has recommended 95 since it involves lesser effort for them.. This does not give us enough leg room since the volumes are not particularly high.. Who decides 95 or 98?
2) response distribution – while I have recommended 50% as it’s a new client and 2r are just ramping up, the client is pushing to change this to 95 or. 98 so their sample drops… How do we challenge this?
3) for low volume processes where the sample size calc throws a low sample.. How can we establish a minimum sampling criteria given that it allows us a vendor to allow for very few / no errors.September 17, 2018 at 5:14 am #203039
You will have to provide some more detail because, as written, your questions are not clear.
1. You say confidence level 95 vs 98. – This can be taken several different ways and each of them will result in a different response.
a. You mean you want to compute the confidence interval around your measurements of process output and you are debating whether or not to compute the 95% or the 98%. If this is what you mean then most of what you have written concerning 95 vs 98 doesn’t make sense. If what you want is the confidence interval for ordinary process variation then the “usual” choice is plus/minus 3 standard deviations which corresponds to a 99% CI. In this case there isn’t much of an issue with respect to sample size.
b. You mean you want to be able to detect a shift from some proportion relative to either a proportion of 95% or 98%. To do this you are going to have to state the size of the shift you want to detect and the degree of certainty (the power) that a shift has indeed occurred in order to compute a sample size.
c. You mean something else entirely.
2. You said “response distribution – while I have recommended 50%….” – what does this mean? In particular – what do you mean by a “response distribution” and how does 50% relate to this?
3. You said “for low volume processes where the sample size calc throws a low sample” – as written this makes no sense at all.
If you could expand on some of your questions and provide clarification perhaps I or someone else could offer some suggestions.September 18, 2018 at 9:04 pm #203045
I think you’re missing a key point, John. It’s true that the customer/client sets specification limits but it is your responsibility, not theirs, to assure that variation is within those limits. You shouldn’t be arguing about sample size. Since you’re doing that it suggests that your process is not capable of reliably meeting specifications, and that’s what you need to change.September 19, 2018 at 2:23 pm #203053
@thmurphy I am with @Straydog on this. You negotiate this before you get the business. Someone agreed to it from your company. I assume you have a process to change things between you and your customer. A formal process. You follow that process but I would caution you to step back a minute and remember this is your CUSTOMER. You might call them a client for whatever reason you choose but that is a customer. You are screwing around over things you have agreed to rather than fixing your process.
I have no clue what you are talking about in most of this but you need to take the CL on the same set of data and plot them out so you can visually see what they look like. 98% is going to be wider than 95%. so how does a 95% give you more room?
You must be logged in to reply to this topic.