rand.design.RC {crossdes}R Documentation

Simulation Study to Asses the Validity of a Randomization Procedure

Description

The function performs a simulation study to assess whether randomization of treatment labels and rows (subjects) validates the row-column model for a given design. The results are stored to a file.

Usage

rand.design.RC(design, dat, tau1, rho, n, where)

Arguments

design A matrix with b rows and k columns representing the experimental design. Treatments are numbered 1,...,trt.
dat A numerical vector with bk elements giving the data to be used for the simulation study. The first k values of dat correspond to the first row of the design, the next k values correspond to the second row etc.
tau1 The value of the main effect of treatment 1.
rho The value that is used for the carryover (residual) effects of treatments 1 and 2.
n The number of permutations in the simulation study.
where Path that gives the location of the simulation results.

Details

The simulation study proceeds as follows: For every iteration, treatment labels and rows of the design are randomized. Then the elementary contrast tau_1 - tau_trt is estimated and the estimate of the variance of this contrast is computed. These computations are done for each of six situations: 1) There are no direct or residual effects of treatments. 2) There is a direct effect of treatment 1. In 3) and 4), a residual effect of treatment 2 is added while in 5) and 6), a residual effect of treatment 1 is added. The estimates are then stored to where.

Value

There is no value returned. The results are stored in a file.

Note

You need to call analyze.rand to display and interpret the results. rand.design.RC just performs the simulation study.

Author(s)

Oliver Sailer sailer@statistik.uni-dortmund.de

References

Bailey, R.A. and Rowley, C.A. (1985): Valid randomization. Proceedings of the Royal Society London A 410, 105-124.

Kunert, J. and Sailer, O. (2006): On nearly balanced designs for sensory trials. Food Quality and Preference 17, 219-227.

See Also

analyze.rand, rand.design.azais

Examples

## Not run: 
 
# First create a data set to analyze:
d <- matrix(c(1:4,2:4,1,4,1:3,3,4,1,2),ncol=4)
rand.design.RC( d, rnorm(16), -1, 1, 1000, "D:\mytest.txt" )
# Now do the analysis:
analyze.rand( "D:\mytest.txt", fig=TRUE, ref=TRUE, 
 refval=c(0, -1, 0, -1, -.25, -1.25) ) 
## End(Not run)

[Package crossdes version 1.0-9 Index]