planor.harmonize: Harmonize the Factors
In planor: Generation of Regular Factorial Designs

Description Usage Arguments Value Note Author(s) Examples

Harmonize the factors originating from a list of factors, a list of models, and a list of basic factors (this function is essentially for internal use).

1 2	planor.harmonize(factors, nlevels, ordered, hierarchy, model, estimate, listofmodels, base)

`factors`	an object of class `designfactors`, typically an output from `planor.factors`). Otherwise the arguments `factors`, `nlevels`, `ordered`, `hierarchy` follow the syntax of `planor.factors`.
`nlevels`	see `planor.factors`. Ignored if `factors` is of class `designfactors`.
`ordered`	see `planor.factors`. Ignored if `factors` is of class `designfactors`.
`hierarchy`	see `planor.factors`. Ignored if `factors` is an object of class `designfactors`.
`model`	a list of model-estimate pairs of formulae, typically an output from `planor.model`. Otherwise the arguments `model`, `estimate` and `listofmodels` follow the syntax of `planor.model`.
`estimate`	see `planor.model`. Ignored if `model` is a list.
`listofmodels`	see `planor.model`. Ignored if `model` is a list.
`base`	an optional formula to specify the basic factors. These factors must belong to the `factors` argument

An object of class designfactors very similar to factors, but with two additional logical columns in slots fact.info and pseudo.info:
- model (TRUE for the factors present in at least one model formula),
- basic (TRUE for the basic factors).

This function is called at the start of the design search. It is essentially a check that the factors in all three arguments are coherent, even though it performs some additional tasks. The function stops if it detects a model or basic factor that is absent from factors. This is because the number of levels of such a factor is unknown and so the design search cannot proceed. Besides, the function eliminates the factors that do appear neither in model nor in base and it reorders the factors by putting first the basic ones.

Monod, H. and Bouvier, A.

F2 <- planor.factors(factors=c("block",LETTERS[1:4]), nlevels=c(6,6,6,4,2))
M2 <- planor.model( model=~block+(A+B+C)^2, estimate=~A+B+C )
F2.h <- planor.harmonize(factors=F2, model=M2, base=~A+B)
names(F2)
names(F2.h)