Fractional factorial design
Builds on Factorial experimentFinite fieldSubgroup
Definition
Let , and code the levels of two-level factors as . Then the runs of the full factorial experiment are the points of . For a subset , called a word, write for . Identify words with vectors of , with the symmetric difference as addition. A regular fractional factorial design is a set of runs where:
- is a subgroup of of order , the defining relation, with no word of size ;
- the signs satisfy and , so that is not empty.
Then has runs. Two effects with words and are aliased if . The resolution of the design is the smallest size of a nonempty word of .
Remarks
On , the contrast columns and of aliased effects agree up to the sign , so their effects cannot be separated. Here is the field with two elements.
Example: , , with , that is, the generator and the defining relation . The runs are , , , , four of the eight. The main effect , with word , is aliased with , since . The design has resolution III.
Non-example: the four runs with form the set , which uses the word of size , so clause 1 fails. In these runs factor never changes, so its main effect cannot be estimated at all.
Reading path
To understand this page from the ground up, read these 4 pages in order. The foundations come first.
Show the path as a graph
- no evidence level
- Factorial experiment concept
- Finite field concept
- Subgroup concept
- Fractional factorial design definition
Further reading
About this page
| Tag | 10WTA1QZXD |
|---|---|
| URI | m2://10WTA1QZXD |
| Kind | definition |
| Writing | W0 stub |
| MSC | 62K15 |
| Defines | Fractional factorial design |
| Uses | Factorial experiment, Finite field, Subgroup |
Markdown · JSON · Edit on GitHub
What this page needs for W1
- an inventory row: the row of the inventory that the node accounts for (0 of 1)
- a source with a locator (0 of 1)
The writing levels say how complete the text of a page is. They do not measure its truth.
What links here
No page links to this page yet.