FrF2: utilitiesV – R documentation

Pricing

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

Get Started for Free

Documentation

FrF2

utilitiesV

~~ Internal utility functions for generating regular fractional factorials ~~

Description

~~ Internal functions, mainly for generating designs without relying on a catalogue of designs ~~

Usage

revdigits(obj, ndigits = 1 + floor(log2(max(obj))))

indexcalc(obj, k = 1 + floor(log2(max(obj))))

gencalc(gen)

YatesFly(walshindex, k=NULL)

Arguments

`obj`	non-negative integer (vector) with Yates matrix column numbers (called Walsh indices by Sanchez and Sanchez 2005)
`ndigits`	number of binary digits; default is the necessary number for the largest element of `obj`
`k`	number of base factors; default is the minimum necessary number for the maximum of `obj`
`gen`	generators in any admissible format (`gen.check` transforms any admissible format to the default needed for calculations))
`walshindex`	non-negative integer (vector) with Yates matrix column numbers (called Walsh indices by Sanchez and Sanchez 2005; must contain the base column numbers 1, 2, 4, 8 and so forth for the desired dimension; if this rule is violated, the first non-base column(s) are omitted in favor of supplementing the set of base columns)

Details

These internal functions are used for generating regular 2-level fractional factorials. The Sanchez and Sanchez (2005) way of providing large resolution V designs is supported, as well as manual design generation of large designs with functions FrF2 and FrF2Large.

Value

revdigits creates a matrix with 0-1 entries in an order appropriate for creating character generators from Yates matrix column numbers,
indexcalc calculates a named list of vectors of base column numbers, named by the corresponding character generator,
gencalc calculates Yates column numbers from arbitrary types of generator representations (except for negative numbers),
YatesFly produces an experimental plan from a vector of Yates column numbers which have to include the base column numbers (contrary to the generators option in FrF2 or FrF2Large

Note

This package is still under development, but does already provide useful and well-tested results.

Author(s)

Ulrike Groemping

References

Sanchez, S.M. and Sanchez, P.J. (2005). Very Large Fractional Factorial and Central Composite Designs. ACM Transactions on Modeling and Computer Simulation 15, 362-377.