Quality Management System Glossary: A-B
A
The maximum number of defects or defectives allowed in a sample from a lot (batch) of product to consider that lot acceptable.
Also known as
Acceptable Quality Limit, Acceptance Quality Level, Acceptable Quality Level, or
AQL level.
The AQL is the lowest tolerable average (mean) of a process in percentage or ratio that is still considered acceptable.
A method of inspection in which statistical sampling of a lot (batch) of product is used to determine whether that lot of product is acceptable. Acceptance sampling comprises two types: attribute sampling and variable sampling.
- Attribute sampling is a statistical method by which the lot is accepted or rejected based on one sample. The sample is recorded as a pass or fail depending on the number of defects or defectives found within that sample when compared to the Acceptance Number. Attribute inspections are typically subjective (visual) interpretations of the product.
- Variable sampling is similar to attribute sampling. However, rather than recording the number of defects, each piece within the sample from the lot of product is measured and those values are assessed against a specification limit. The result of that assessment may indicate the lot passes or fails. Sample sizes for variable sampling are usually smaller than attribute sampling because measurements are more accurate than subjective interpretation.
The specific criteria by which a product is to be examined for acceptance utilizing
Acceptance Sampling methods. The size of the lot (batch) of product combined with the
Acceptance Quality Limit, as well as other considerations (depending on the plan being used and the characteristics being inspected), determine the sample size as well as the acceptance number. Some of the most commonly used standards today are ANSI/ASQ z1.4 (Attributes), ANSI/ASQ z1.9 (Variables), Lot Tolerance Percent Defective (LTPD), and Zero Acceptance Number (as described by Nicholas Squeglia in
Zero Acceptance Number Sampling Plans, ASQC Quality Press).
The difference of agreement between an observed value and an accepted reference value.
A statistical procedure for troubleshooting industrial processes and analyzing the results of experimental designs with factors at fixed levels. When you need to compare multiple group means, you can use the ANOM as an alternative to the one-way analysis of variance
F.
Also known as
Variance Analysis,
ANOVA Variance,
ANOVA Analysis.
A basic statistical technique for determining the proportion of influence that a factor, or set of factors, has on total variation. ANOVA tests for differences between means; it's similar to many other tests and experiments in that its purpose is to determine whether the response variable (i.e., your dependent variable) is changed by manipulating the independent variable.
Also known as
AS9100 Standard and
AS9100 Quality.
A widely adopted and standardized quality management system for the aerospace industry. It is known as EN9100 in Europe and JISQ9100 in Japan.
Also known as
Assignable Cause Variation.
An identifiable, specific cause of variation in a given process or measurement. Also see
Special Cause.
Also known as
Go/No-Go information.
Qualitative data that can be counted for recording and analysis. Control charts based on attribute data include: percent chart, number of affected units chart, count chart, count-per-unit chart, quality score chart, and demerit chart. Also see
Go/No-Go.
See
Mean.
Also known as
Averages Control Chart.
A control chart in which the subgroup average, X-bar, is used to evaluate the stability of the process level. Also see
X-Bar Chart.
Also known as
Average Outgoing Quality Formula.
The expected average quality level of an outgoing product for a given value of incoming product quality. Depends on the incoming quality, the probability that the lot will be accepted, and the sample and lot sizes.
Represents the maximum percent defective in the outgoing product. AOQL is the maximum average outgoing quality over all possible levels of incoming quality for a given acceptance sampling plan and disposal specification.
The number of points, on average, that will be plotted on a control chart before an out-of-control condition is indicated (e.g., a point plotting outside the control limits).
B
An imperfection severe enough to be noticed but that should not cause any real impairment with respect to the intended normal, or reasonably foreseeable, use. Also see
Defect,
Imperfection, and
Nonconformity.
The offset of a measured value from the true population value.
Also known as
Binomial Distribution Formula.
A discrete probability distribution used for counting the number of successes and failures or conforming and nonconforming units. This distribution underlies the
p-chart and the
np-chart.
A plot used in exploratory data analysis to picture the centering and variation of the data based on quartiles. After the data are ordered, the 25th, 50th, and 75th percentiles are identified. The box contains the data between the 25th and 75th percentiles.