logit.cont: Assuming a logistic model for the response, allocate a...
In mst1g15/biasedcoin:

Assuming a logistic model for the response, allocate a continuous treatment sequentially based on an information matrix-based optimality criterion. Responses are simulated assuming the true parameter values.

1
2
3

logit.cont(covar, true.beta, init, int = NULL, lossfunc = Dopt.y.t,
  same.start = NULL, rand.start = NULL, bayes = T, u = NULL,
  true.bvcov = NULL, ...)

`covar`	a dataframe for the covariates
`true.beta`	the true parameter values of the data generating mechanism
`init`	the number of units in the initial design
`int`	set to T if you allow for treatment-covariate interactions in the model, NULL otherwise
`lossfunc`	the objective function to minimize
`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.
`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>

design matrix D, responses y, all estimates of betas, final beta, probabilities for treatment assignment, proportion of Y=1, proportion tmt=1, values of objective function

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