Average Outgoing Quality

AOQ - Average Outgoing Quality: The average quality level leaving the inspection point after rejection and acceptance of a number of lots. If rejected lots are not checked 100% and defective units removed or replaced with good units, the AOQ will be the same as the AIQ.

Average Incoming Quality

AIQ - Average Incoming Quality: This is the average quality level going into the inspection point.

Average of a statistical sample

Also called sample mean, it is the arithmetic average value of all of the sample values.  It is calculated by adding all of the sample values together and dividing by the number of elements(n) in the sample.

Autocorrelation

Autocorrelation means that the observations are not independent. Each observation will tend to be close in value to the next. This can result in under estimating sigma. A little bit of autocorrelation will not ruin a control chart.

Audit

A timely process or system, inspection to ensure that specifications conform to documented quality standards. An Audit also brings out discrepencies between the documented standards and the standards followed and also might show how well or how badly the documented standards support the processes currently followed.

Corrective, Preventive & Improvement Actions should be undertaken to mitigate the gap(s) between what is said (documented), what is done and what is required to comply with the appropriate quality standard. Audit is not only be used in accounting or something that relates to mathematics but also used in Information Technology.

Attribute Data

Attribute data is the lowest level of data. It is purely binary in nature. Good or Bad, Yes or No. No analysis can be performed on attribute data.

Attribute data must be converted to a form of Variable data called Discrete data in order to be counted or useful.

It is commonly misnamed discrete data.

Attribute Charts

Attribute chart opportunities exist in any technical or administrative process. The most significant difficulty is to develop precise operational definitions of what is "nonconforming".

Assurance

Providing an optimal degree of confidence to Internal and External Customers regarding establishing and maintaining in the organization, practices, processes, functions and systems for accomplishing organizational effectiveness.

Establishing and maintaining an optimal degree of confidence in the organizational practices, processes, functions and systems for accomplishing organizational effectiveness.

Alternate definition:
Establishing and maintaining the commitments made to Internal and External Customers.

Assignable Variations

Variations in data which can be attributed to specific causes.

Assignable Cause

A source of variation which is non-random;  a chang in the source("Vital few" variables) will produce a significant change of some nagnitued in the resonse(dependent variable), e.g., a correlation exists; the change nay be due to an intermitent in-phase effect or a constant cause system which may or may not be highly predictable; an assignable cause is often signaled by an excessive number of data points outside a control limit and/or a non-random pattern within the control linits; an unnatural source of variation; most often economical to eliminate.

A-square

A-squared is the test statistic for the Anderson-Darling Normality test. It is a measure of how closely a dataset follows the normal distribution. The null hypothesis for this test is that the data is normal. So if you get an A-squared that is fairly large, then you will get a small p-value and thus reject the null hypothesis. Small A-squared values imply large p-values, thus you cannot reject the null hypothesis.

Arrhenius model

This model suggests that degradation leading to component failure is governed by a chemical and physical process reaction rate.

Anderson-Darling Normality Test

After you have plotted data for Normality Test, Check for P-value.

P-value < 0.05 = not normal.

normal = P-value >= 0.05

Note: Similar comparison of P-Value is there in Hypothesis Testing.
If P-Value > 0.05, Accept H0

Analysis of variance(ANOVA)

Analysis of variance is a statistical technique for analyzing data that tests for a difference between two or more means by comparing the variances *within* groups and variances *between* groups. See the tool 1-Way ANOVA.

Analysis of means(ANOM)

A graphical analysis approach to compare the means of seberal groups of size.

Analysis of Covariance

When we can observe the value for a factor, it can be compensated for using analysis of cobariance techniques.

American Society for Quality

In my opinion an organization should choose a common computer program that offers many statistical tools, ease of use, good pricing, and technical support.

Alternative Hypothesis(Ha)

The alternate hypothesis (Ha) is a statement that the means, variance, etc. of the samples being tested are not equal. In software program which present a p value in lieu of F Test or T Test When the P value is less than or equal to your agreed upon decision point (typically 0.05) you accept the Ha as being true and reject the Null Ho. (Ho always assumes that they are equal).

Alpha Risk

Alpha risk is defined as the risk of rejecting the Null hypothesis when in fact it is true.
Synonymous with: Type I error, Producers Risk
In other words, stating a difference exists where actually there is none. Alpha risk is stated in terms of probability (such as 0.05 or 5%).
The value (1-alpha) corresponds to the confidence level of a statistical test, so a level of significance alpha = 0.05 corresponds to a 95% confidence level.

Aliasing

Lost interactions in a Design of Experiment. An alias indicates that you've changed two or more things at the same time in the same way. Aliasing is a critical and often overlooked feature of Plackett-Burman, Taguchi designs or standard fractional factorials. Aliasing is a synonym for confounding.