Design of Experiments Terminology

Design of Experiments Terminology can be daunting! Here’s an easy glossary to use when working on Design of Experiments Terminology questions.

Alias Structure

Alias structures are used in Fractional Factorial designs to determine which combinations of factors and levels will be tested.

Balanced Experiment

Each factor appears the same number of times.

Blocking

Blocking recognizes uncontrolled factors in an experiment–for example, gender and age in a medical study–and ensures as wide a spread as possible across these Nuisance Factors. Read more about Blocking.

Classification factor

A Classification Factor is an element that cannot be defined or set by the experiment designer but can be used in sample selection. For example, the sex of a subject is an example of a Classification Factor.

Confounding

Confounding occurs when we can’t be sure which factors – or combinations of factors – affect a result. Blocking can help to minimize Confounding.

Experimental factor

An Experimental Factor is one that can be changed and set by the person who designs the experiment.

Experimental Notation

Experiments can use numbers to shorten their notation.

2^5 means that there are 5 factors at 2 levels.

Factor

Factors are elements in your experiment – whether in your control or outside of it – that affect the results. Read more about factors.

Fractional Factorial

Experiment design that tests only a subset of the possible factor-level combinations. Read more about Fractional factorial.

Full Factorial

Experiment design that tests the full set of possible factor-level combinations. Read more about the full factorial.

Interaction

Factor Interactions occur when multiple factors affect the output of an experiment.

Level

Every treatment factor in an experiment will have at least two levels. These might be minimum and maximum values, discrete groups (for example, ‘male’ and ‘female’), or designated ranges (for example, ages 25-34; 35-44; etc.).

Nuisance Factor

A Nuisance Factor is the opposite of a treatment factor–an element that is of no interest to the experiment but needs to be considered anyway in case it skews results.

Qualitative Factor

A Qualitative Factor is a treatment factor that has a number of categories.

Quantitative Factor

A Quantitative Factor is a treatment factor that can be set to a specific level as required.

Randomization

Randomization is essentially when a person conducts trials in no pre-determined order. There’s no reason to believe conducting trials randomly will cost less (in fact, it may very well cost more), but it helps overcome (or avoid) bias. It also means that noise factors are equally likely to be present in all trials.

Replicates

Replicates are multiple experimental runs of the same factors and experiments. You do this to get a sense of the variability in the data set. Good article on Replicates and Repeats here from MiniTab.

Replication

Replication means more trials, thus more costs, but it only allows you to study whatever interactions the original trials already allowed you to study. It also allows for the estimation of experimentation errors.

Resolution

Resolution tells us the Confounding we will see between factors.

Treatment Factor

A treatment factor is an element that is of interest to you in your experiment because you will manipulate it to test your hypothesis.

Six Sigma Black Belt Certification Design of Experiments Terminology Questions:

Question: Which of the following best describes a controlled variable whose influence on a response is being studied? Taken from (ASQ sample Black Belt exam.)

(A) Replicate
(B) Version
(C) Level
(D) Factor

Answer:

C: See how the responses for each element (B+ and B-) are completely different when the factors are changed (from A- to A +)? In choice A, both elements move up in lock-step. They agree. In choice B, both elements drop–yes, one more precipitously than the other. But both agree. Similarly, in choice D – both elements hold steady despite the factors changing. That leaves choice c as the factorial experiment with the strongest interaction. See Factorial Design Terminology.