Reduce Inspection Costs with Sequential Sampling

William A. Levinson, P.E., is Keynote Speaker at ComplianceKey. He is the principal of Levinson Productivity Systems, P.C. He is an ASQ Fellow, Certified Quality Engineer, Quality Auditor, Quality Manager, Reliability Engineer, and Six Sigma Black Belt. He is also the author of several books on quality, productivity, and management, of which the most recent is The Expanded and Annotated My Life and Work: Henry Ford's Universal Code for World-Class Success.


ANSI/ASQ Z1.4 (formerly MIL-STD 105) is a generally accepted standard for acceptance sampling by attribute (pass/fail) data. Sampling plans are defined by a sample size of n and an acceptance number c, and lots are accepted if the sample contains c or fewer nonconformances or defects. Double sampling and multiple sampling plans seek to reduce the amount of inspection by accepting very good lots quickly, and rejecting very bad lots just as quickly. Sequential sampling plans minimize inspection by inspecting one item at a time and using statistically calculated decision limits to accept or reject the lot.

Why should you attend this webinar?

Inspection is a necessary but non-value-adding activity, which means the organization should do as little as possible as long as the inspection plan meets customer requirements for quality assurance. Sequential sampling is the most efficient procedure for sampling by attributes, and any ANSI/ASQ Z1.4 plan can be converted into a sequential sampling plan with roughly equivalent performance in terms of the operating characteristic curve. This webinar will begin with an overview of ANSI/ASQ Z1.4, and then show how to convert any of its normal or tightened inspection plans into a sequential sampling plan. The situation for reduced inspection is somewhat more complicated but, as inspection is in fact reduced, less is to be gained in this case from a sequential plan.

Areas Covered in the Session:

An ANSI/ASQ Z1.4 sample plan is defined by a sample size n and acceptance number c. These define the producer's risk (alpha) of rejecting a lot at the acceptable quality level (AQL), and this risk is generally targeted at 5%. These plans do not include official rejectable quality levels (RQLs) but, for the purpose of development of a sequential plan, we can treat the quality level at which the rejection probability is 90% as the RQL. (The latter also is the foundation of zero acceptance plans.)
A sequential sampling plan can then be defined by two points on the operating characteristic (OC) curve. These are (AQL, alpha) and (RQL, beta) where beta, the consumer's risk of accepting a lot at the RQL, is traditionally 10 percent. The resulting plan has acceptance and rejection numbers for every successive item that is inspected, which is not particularly convenient because it may have dozens or even more than a hundred rows. This presentation will, however, show how to organize the plan according to acceptance and rejection sample sizes that depend on the number of nonconforming items that have already been found. This reduces the tabulated sample plan to perhaps a dozen rows, or even fewer, thus overcoming a long-standing practical obstacle to sequential sampling plans.
The webinar will then show how compute the operating characteristic (OC) curve, which plots the chance of acceptance versus the actual nonconforming fraction. The result is comparable to the OC curve for the corresponding ANSI/ASQ Z1.4 plan, and matches it exactly at the two design points (AQL, alpha) and (RQL, beta).
The average sample number (ASN) can also be calculated versus the actual nonconforming fraction, and will be lower than that for the corresponding ANSI/ASQ Z1.4 plan.
Sequential sampling plans can also be used for tightened ANSI/ASQ Z1.4 plans (per the switching rules) but the issue of reduced sampling is more complex because two decisions-whether to accept the lot and whether to invoke the switching rules to return to normal inspection-are involved. However, less is to be gained from sequential sampling for reduced inspection.

Attendees will receive an Excel spreadsheet that is programmed to calculate sequential sampling plans based on the points (AQL, alpha) and (RQL, beta)

Who can Benefit:

Quality inspectors, technicians, and engineers

Webinar Id: LSHCWR001

Training Options:

Duration: 60 mins

 Stop, pause, and rewind: learn at your own place.

No reviews yet!!
 Recorded: [Six month unlimited access]

 $167 (Single Attendee)  $599 (Unlimited Attendee)

Refund Policy
Past Webinar of William A. Levinson
Process Capability Analysis
Presenter: William A. Levinson
View it anytime
Price: $167
How to Perform Measurement Sys....
Presenter: William A. Levinson
View it anytime
Price: $167

More Webinar

Pay Pal Logo   PayPal Verified Logo   GoDaddy Certified
Copyright © 2020 Compliance Key . All Rights Reserved. Back to Top