future.coordex: Calculates expected optimality for a given trajectory after...

In mst1g15/biasedcoin:

Description

Calculates expected optimality for a given trajectory after allocating treatments to the trajectory with the coordinate exchange algorithm

Usage

future.coordex(D.fix, n.r, n, k, sim, int, z.probs, code = NULL, lossfunc,
  ...)

Arguments

D.fix	Design matrix constructed using the true covariates in the experiment so far
n.r	length of trajectory to be simulated
n	number of total patients
k	number of "outer loops" in the coordinate exchange algorithm
sim	number of trajectories to simulate
int	set to T if you allow for treatment-covariate interactions in the model, NULL otherwise
z.probs	vector of probabilities for each level of covariate z
code	set to NULL if (-1,1) coding is used for the treatments. Set to 0 if (0, 1) is used.
lossfunc	the objective function to minimize
...	further arguments to be passed to <lossfunc>

Value

loss of the design matrix which includes trajectory

mst1g15/biasedcoin documentation built on Nov. 26, 2019, 4:01 a.m.