rcDiGGer {DiGGer}R Documentation

Function to search for a row-column design using DiGGer.

Description

rcDiGGer modifies a DiGGer object to search for a row-column design.

Usage

rcDiGGer(numberOfTreatments, rowsInDesign, columnsInDesign,
rowsInReplicate = NULL, columnsInReplicate = NULL,
twoPhase = TRUE, nested = TRUE, fixedBlocks = FALSE,
blockGammas = list(rGamma = 1, cGamma =1), aType = NULL,
targetAValue = 0, maxInterchanges = 1e+05,
searchIntensity = c(0,100), runSearch = TRUE,
rngSeeds = NULL, rngState = NULL, treatName = NULL,
treatNumber = NULL, treatRepPerRep = NULL, treatGroup = NULL,
initialDesign = NULL, initialSwap = NULL)

Arguments

numberOfTreatments

The number of treatments in the design.

rowsInDesign

The number of rows in the design.

columnsInDesign

The number of columns in the design.

rowsInReplicate

The number or rows in the template replicate block.

columnsInReplicate

The number of columns in the template replicate block.

twoPhase

If TRUE the bigger block is optimised in the first phase of the search and the smaller in the second phase. The order of the optimisation can be specified as "rowThenCol" or "colThenRow". If FALSE both blocks are optimised in one search phase.

nested

If TRUE blocks do not extend past replicates. If a pair of numbers given, the first is the number of rows in a column-block, the second is the number of columns in a row-block. If nested is FALSE, row and column blocks extend across the whole design.

fixedBlocks

Logical value whether blocks are treated as fixed.

blockGammas

Variance component assigned to random row blocks, rgamma and random column blocks, cgamma.

aType

A DiGGer A-measure type: "A++", "Agg", "A22", "A11", "A1+", "Aa2" or "Aaa". The default is "A++" for equally replicated treatments, "Agg" for unequal replication.

targetAValue

The search stops in each search phase when the A value is below this value.

maxInterchanges

number of treatment interchanges to test in each search phase. If twoPhase = TRUE two numbers may be given.

searchIntensity

Percentage of possible interchanges to consider for non-improving interchanges. Two figures may be given for two phase searches.

runSearch

Logical value, whether to run the search immediately.

rngSeeds

Seeds c(s1,s2) to control the DiGGer search. s1 must be in the range [0,31328], s2 must be in the range [0,30081].

rngState

Current state of the random number generator.

treatName

Vector of treatment names to be associated with the design numbers.

treatNumber

Vector of treatment numbers to be associated with the design numbers.

treatRepPerRep

Vector of replication levels for each treatment within each replicate template block.

treatGroup

Vector of group codes (up to 200 distinct values) associated with treatments. Group codes may be used to modify the A-efficiency measure in the optimisation.

initialDesign

A matrix rowsInDesign by columnsInDesign giving design numbers in the initial design.

initialSwap

A dimension pair or a matrix rowsInDesign by columnsInDesign of swap codes. Only plots with the same swap code may have treatment interchanges during the DiGGer search.

Details

rcDiGGer constructs a framework for a DiGGer row-column design search. Row-column searches may be run in two phases, optimising rows then columns or columns then rows, or in a single phase. Blocks may be considered to be nested within sections of the design. Blocks are treated as random by default. The search may fail with fixed blocks if the blocks become disjointed. When runSearch = TRUE the search is run when rcDiGGer is called otherwise the run function may be called to run the search.

If there is more than one treatGroup code the search may optimise comparisons between treatments in different treatment groups, aType="Agg". If aType=NULL the default code for equally replicated treatments is "A++" and for unequal replication it is "Agg".

Value

A DiGGer search object.

ddphase

A list with an element for each phase of the search. An element is populated with seeds, design, aMeasures and lastImprovement as each search phase is completed.

dlist

A dataframe of the design after a search has been run().

Author(s)

Neil Coombes

References

Coombes, N.E. (2002) The Reactive Tabu Search for Efficient Correlated Experimental Designs. PhD Thesis, Liverpool John Moores University.

Examples

# Example of search run for 12 treatments
# in 3 3-row by 4-column replicates
# and default nested rows and columns
rc12 <- rcDiGGer(12, 3,12, 3,4)

[Package DiGGer version 1.0.5 Index]