# Looking for Information on Process Inspections Regarding Sample Size and Frequency

Six Sigma – iSixSigma › Forums › General Forums › General › Looking for Information on Process Inspections Regarding Sample Size and Frequency

This topic contains 2 replies, has 3 voices, and was last updated by Mike Carnell 6 months, 4 weeks ago.

- AuthorPosts
- January 19, 2019 at 1:04 pm #235546

WsdmseekerParticipant@Wsdmseeker**Include @Wsdmseeker in your post and this person will**

be notified via email.I need to establish inspections for a production process, and I need to determine the sample size and the frequency of it. What I am looking for, is the theoretical information to support this project, is there any bibliography, norm, manual, video, etc. That you could recommend me to back my project up?

1January 20, 2019 at 12:01 am #235555

StrayerParticipant@Straydog**Include @Straydog in your post and this person will**

be notified via email.You can find a lot of information on calculating sample size by searching this site. You can also find sample size calculators on the net if you’d rather not do the math. You need to know your population size (total units produced in a given period), standard deviation for the population (often estimated since measuring the entire population may be cost prohibitive), and your desired level of confidence (typically 95%). Are your measurements variables (potentially infinite variation depending how many decimal places) or proportional (discrete) where there is a fixed number of values such as A,B,C…? There are different formulas depending on that but some argue that you only need the standard formula. Regarding how often you should sample, this depends on cost/benefit and stability of your process.

For research you might want to start with this Wikipedia article https://en.wikipedia.org/wiki/Sample_size_determination

I’d advise you to just start doing it with whatever sample size is practical rather than trying to determine your optimum sample size at first. Management will often accept this because it’s a good thing to do, if it doesn’t cost too much. You’ll soon learn whether your samples are too large or too small. Just beware that you can only speak about defects found in the sample until you have a statistical basis for sampling.

0January 21, 2019 at 10:33 am #235591

Mike CarnellParticipant@Mike-Carnell**Include @Mike-Carnell in your post and this person will**

be notified via email.There is a book called Statistical Quality Control by Grant and Levenworth. There is Sampling theory in this book.

My copy is old so I am not sure what the current revision looks like but it was a great book if you want to understand sampling theory beyond just understanding how to look things up in a table. They will teach you (help you teach yourself) the Poison Distribution and OC Curves which are the foundation to sampling. Just as an example people are all enamored with C=0 sampling plans. If you understand OC Curves then you realize they are very inefficient plans to help you accomplish what you are trying to do.

Just my opinion.

0 - AuthorPosts

You must be logged in to reply to this topic.