Design safe acceptance plans!

Supplier Sampling plans

The estimate of the value of a product characteristic depends upon the method of analysis used, and on the method of sampling used. The relationship between the value and the method of analysis to estimate that value can be easily appreciated, but the association between the value of the characteristic and the method of sampling is not so clearly understood.

Sampling plans are required in order to ensure that fair and valid procedures are used when food is being controlled for compliance with a specification standard. People responsible accepting a material from a supplier should select a sampling plan that is appropriate for statistical inspection of the lot received. No sampling plan can ensure that every item of a lot is within specification. Food sampling of course is destructive in the majority of the inspection cases. Sampling plans are however at least useful to guarantee an acceptable quality level.

The definition of an acceptance sampling procedure will require the setting or selection of the characteristic to be measured, the lot size, the selection of an attribute or variables plan, the Limiting Quality (LQ) level (for isolated lots) or the acceptable quality level (AQL) for a continuous series of lots, the level of inspection, the size of the sample, the criteria for acceptance or rejection of the lot and the procedures to be adopted in cases of dispute.

Sampling procedures involve the selection of samples from a lot, the analysis of the samples, and the classification of the lot as acceptable or not acceptable based upon the result of the analysis of the sample. An acceptance sampling plan is a set of rules by which a lot is to be inspected and classified. The plan will stipulate the number of items, randomly selected from the lot under inspection, which will comprise the sample. A sampling procedure which involves switching from one sampling plan to another is referred to as a sampling scheme or sampling level. A collection of sampling plans and sampling schemes constitutes a sampling system.

One of the criteria that can outline the quality of a lot is the AQL for a chemical, physical or microbiological specification of a food product. Τhe AQL in a lot is the percentage of defective items that is considered satisfactory as a process average and is accepted with a given high probability of acceptance, varying usually from 90% to 99%. Different AQLs, suppose much different sampling numbers.

For a given sampling plan, an Operating Characteristic (OC) curve describes the probability of acceptance of a lot as a function of its actual quality. It relates the rate of defective items in lots with the probability of accepting these lots at control. On the OC curve of a sampling plan, the producers' risk corresponds to the probability to wrongly (according to the producer) reject a lot. The consumers' risk corresponds to the probability to wrongly (according to the customer) accept a lot. The discrimination distance (D) is the absolute distance between the producers' risk (PR) and the consumers' risk (CR).

The inspection level relates the sample size to the lot size and hence to the discrimination afforded between good and poor quality. A sampling scheme involves switching between normal, tightened and reduced inspection sampling levels. Normal inspection is designed to protect the producer against having a high proportion of lots rejected when the quality of the product is better than the AQL. However, if two out of any five (or fewer) successive lots are not accepted, then tightened inspection must be introduced. Normal inspection can only be restored when five successive lots have been accepted under tightened inspection. On the other hand, if production quality is consistently better than the AQL, sampling costs may be reduced by the introduction of reduced-inspection sampling plans. This can be the case when the preceding 10 lots (or more) have been subjected to normal inspection and all have been accepted, and production is at a steady state.

Quantitative results should be accompanied by some estimate of the random and systematic errors in them. Sampling plans are associated with two types of error: sampling error (caused by the sample failing to accurately represent the population from which it was collected) and measurement error (caused by the measured value of the characteristic failing to accurately represent the true value of the characteristic within the sample). It is desirable that the sampling errors associated with any sampling plan, as well as the measurement errors associated with the analysis should be quantified and minimized. When the controlled characteristics need to be analyzed, any decision on a lot from a sample shall take into account the measurement uncertainty, in comparison with the sampling error.

There are numerous sampling plans available for your raw materials. PES is familiar with their pitfalls and advantages, and can propose you and implement the best one in terms of efficiency and cost. PES can also support the movement away from an AQL-based inspection strategy to implementation of a prevention-based strategy supporting continuous improvement.

More information