Menu.facTab1: Basic information for full factorial designs

Menu.facTab1R Documentation

Basic information for full factorial designs

Description

This help file describes usage of the basic information tab of the full factorial design menu

Brief statistical background

Full factorial designs consist of all possible combinations of factor levels, i.e. the number of runs is the product of all numbers of factor levels, for example 24 for an experiment with two 2-level factors and one 6-level factor. Of course, their size grows fast with the number of factors. If a full factorial design is not feasible, orthogonal main effects designs or (manually-generated) combinations of smaller designs may be a reasonable option.

Inputs on Tab Base Settings

name of design

must be a valid name. The design itself is created under this name in the R workspace.

number of runs

is a consequence of the specifications on the Factor Details tab. It is displayed for information purposes only; its value is only valid if the Factor Details tab contains entries for all factors.

number of factors

must always be specified. The number of factors must match the number of entries on the Factor Details tab.

replications

is the number of times each experimental run is conducted. If larger than 1, each run is conducted several times. If the checkbox next to the number of replications is checked, it is assumed that the experiment involves repeated measurements for one setup of the experimental run; if it is not checked, the experimental run itself is replicated with everything relevant newly set up (much more valuable than repeated measurements, unless the key driver of variability is in the measuring step). If the check box is not checked, the experiment will be randomized separately for each round of replications (first all first runs, then all second runs etc.).

number of blocks

is the number of equally-sized blocks of homogeneous units into which the overall number of runs is to be subdivided. Note that the number of blocks must be compatible with the numbers of levels of the experiment: it must be the product of one or more primes that the numbers of levels factor into. For example,
a design with three factors at 2,5 and 5 levels can have 5 blocks or 10 units each, no other blocking is possible for this design because it would confound blocks with factor main effects;
a design with three factors at 2, 6 and 6 levels can have 2, 3, 6, 4 or 12 blocks, because all these numbers of blocks can be obtained from the three 2s and two 3s the numbers of levels factor into without confounding a main effect.
An error message will be given whenever an impossible number of blocks or a number of blocks that would require aliasing of blocks with main effects is used; the design is generated with a warning message whenever the block factor is aliased with any two-factor interaction among the design factors.

randomization settings

should normally not be changed; you can provide a seed if you want to exactly reproduce a randomized design created in the past. Unchecking the randomization box will produce a non-randomized experiment. This is usually NOT recommended.

Author(s)

Ulrike Groemping

See Also

See Also fac.design for the function that does the calculations and Menu.General for overall help on the general factorial design menu.


RcmdrPlugin.DoE documentation built on Oct. 7, 2023, 5:07 p.m.