cr.simfuture.logis.cont: Allocate treatments according to weighted L-optimal objective...
In mst1g15/biasedcoin:

View source: R/lopt logistic pseudononmy.R View source: R/lopt_logistic_pseudononmy.R

Allocate treatments according to weighted L-optimal objective function allowing for a pseudo-nonmyopic approach. We assume a logistic model for the response and continuous treatment.

1
2
3

cr.simfuture.logis.cont(covar, true.beta, threshold, kappa, init, sim, z.probs,
  k = 2, wt, prior.scale = 100, same.start = NULL, rand.start = NULL,
  bayes = T, u = NULL, prior.default = T, true.bvcov = NULL, ...)

`covar`	a dataframe for the covariates
`true.beta`	the true parameter values of the data generating mechanism
`threshold`	the cut-off value for hypothesis tests
`kappa`	the value of probability at which weights are set at zero
`init`	the number of units in the initial design
`sim`	number of trajectories to simulate
`z.probs`	vector of probabilities for each level of covariate z
`k`	number of "outer loops" in the coordinate exchange algorithm
`wt`	set to T if the above lossfunction is weighted, NULL otherwise
`prior.scale`	the prior scale parameter
`same.start`	the design matrix to be used for the initial design. If set to NULL, function generates initial design.
`rand.start`	If set to T, function generates an initial design randomly. Else, coordinate exchange is used.
`bayes`	set to T if bayesglm is used instead of glm. Default prior assumed.
`u`	vector of uniform random numbers for generating responses. If set to NULL, responses generated from the binomial distribution.
`prior.default`	set to T if default priors for bayesglm is used. If set to False and bayes=T, normal priors used.
`true.bvcov`	if set to T, use the true parameter values to compute obejctive function. If set to NULL, use estimated parameter values.
`...`	further arguments to be passed to <lossfunc>