Definition of terms used in SQC techniques



Variables are quality characteristics that can be measured on a continuous scale. For example, the diameter of a shaft can be measured by a dial micrometer before taking a decision regarding the quality i.e. whether the diameter is within the permissible limits of variation.


Attributes are quality characteristics which can be classified into one of the two categories namely good or bad, defective or non-defective. For example, a painted surface is good or bad depending on the quality of the workmanship of the painter and the quality of the paint used.

Chance causes of variation:

Chance causes are reasons for minor variations in the quality characteristics that are inspected. These causes do not cause the item to be rejected as the variations are within the limits (i.e. tolerance limits). Chance causes of variation are inherent in the process.

Assignable causes of variation:

These causes are external to the process and cause large variation in quality characteristics making the item liable to be rejected. For example, defective raw materials, faulty machine settings, worn out machine parts or worn out or defective tools cause major variations in quality characteristics and are called as assignable causes of variation. Assignable causes must be identified and eliminated from the process.

Type I error:

This is an error in sampling inspection. A sample from the output of a process may lead to the conclusion, that the process is out of control when, in fact it is operating as intended. Such an error is known as type I error.

Type II error:

This error occurs, when the process is not working as intended, but, sampling error causes one to infer that, the process is satisfactory.

Acceptable quality level (AQL):

Acceptable quality level is the maximum percentage or fraction defective, that is considered as the overall process average. The lots having quality equal to AQL or better have a high probability of acceptance (i.e. 0.95).

Lot tolerance percent defective (LTPD):

This is the upper limit of the percentage of defective products in an individual lot that the consumer is willing to tolerate, even if the process average is acceptable. This is also known as limiting quality level (LQL). Lots having quality equal to LTPD or worse have a very low probability of acceptance. (i.e. 0.10)

Producer’s risk (α):

This is the risk of getting sample which has higher proportion of defectives than the lot as a whole and thereby rejecting a good lot based on sample evidence, i.e. a lot as good as AQL will be rejected by use of a particular sampling plan. While using acceptance sampling plans, producers hope to keep this risk (α) as low as 5%.

Consumer’s Risk (β):

This is the risk of getting a sample which has a lower proportion of defectives than the lot as a whole and thereby accepting a bad lot as a good lot i.e. it is the probability that a lot with a percentage of defective equal to the LTPD will be accepted by the sampling plan. While using sampling plans, consumers want to keep this risk (β) as low as 10%.

Average outgoing quality (AOQ):

In a production process, if the lots that are produced have an average fraction defective p’ and if some of the lots which are rejected based on sample evidence are inspected 100% and the defective units are either simply removed or replaced with non-defective ones, the average quality of the outgoing lots after inspection improves. This average level of quality leaving the inspection operation is called average outgoing quality (AOQ).

“What? Gaming in the workplace? No way!” This is something that we hear from Corporate
Closely tied to the question of how much capacity should be provided to meet forecasted
The notion of focus naturally, almost inevitably from the concept of fit. Just as a
At its heart a capacity strategy suggests how the amount and timing of capacity changes
However, as with most strategic decisions, the issue is more complex than it first appears.