conf.design {conf.design}  R Documentation 
Construct designs with specified treatment contrasts confounded with blocks. All treatment factors must have the sampe (prime) number of levels.
conf.design(G, p, block.name = "Blocks", treatment.names = NULL)
G 
Matrix whose rows define the contrasts to be confounded. The number of columns of 
p 
The common number of levels for each factor. Must be a prime number. 
block.name 
Name to be given to the factor defining the blocks of the design. 
treatment.names 
Name to be given to the treatment factors of the design. If

For example in a 3^4
experiment with AB^2C
and
BCD
confounded with blocks (together with their generalized
interactions), the matrix G
could be given by
rbind(c(A = 1, B = 2, C = 1, D = 0), c(A = 0, B = 1, C = 1, D =
1))
For this example, p = 3
Having column names for the G
matrix implicitly supplies the
treatment factor names.
For a single replicate of treatments, blocks are calculated using the confounded contrasts in the standard textbook way. The method is related to that of Collings (1989).
A design with a Blocks
factor defining the blocks and treatment
factors defining the way treatments are allocated to each plot. (Not
in randomised order!)
None.
Collings, B. J. (1989) Quick confounding. Technometrics, v31, pp107110.
###
### Generate a 3^4 factorial with A B^2 C and B C D confounded with blocks.
###
d34 < conf.design(rbind(c(A = 1, B = 2, C = 1, D = 0),
c(A = 0, B = 1, C = 1, D = 1)), p = 3)
head(d34)
### Blocks A B C D
### 1 00 0 0 0 0
### 2 00 1 2 1 0
### 3 00 2 1 2 0
### 4 00 2 2 0 1
### 5 00 0 1 1 1
### 6 00 1 0 2 1
as.matrix(replications(~ .^2, d34))
### [,1]
### Blocks 9
### A 27
### B 27
### C 27
### D 27
### Blocks:A 3
### Blocks:B 3
### Blocks:C 3
### Blocks:D 3
### A:B 9
### A:C 9
### A:D 9
### B:C 9
### B:D 9
### C:D 9