This function will generate the matrix of deltas, as specified in the paper.
See Details section.
Usage
genDelMat(theta.diff, sigma.2 = 1, n = 1)
Arguments
theta.diff
A vector of length p-1, where p is the number of populations
of treatments. Coordinate [i] in theta.diff corresponds to $\theta_i -
\theta_{i+1}$.
sigma.2
The known variance of the error terms.
n
The number of replications in each population.
Value
The function returns a matrix with p rows and p columns, that
contains the $delta_{ij}$'s, as described in the paper.
Details
As specified in the paper, we can assume that the thetas are in a
decreasing order, meaning that $\theta_1 \ge \theta_2, \ldots, \theta_n$.
It follows that all the components of the theta.diff vector must be positive.
Note that the delta matrix in the paper is a scaled version of the
differences between the thetas.