getOptTm: Computes the Optimal Treatment Mechanism Within a Parametric...

In achambaz/tsml.cara.rct: Targeted Sequential Minimum Loss CARA RCT Design and Inference

Description

Computes the optimal treatment mechanism within a given parametric model of treatment mechanisms. The computation is based on Monte Carlo simulation.

Usage

getOptTm(tm.model = formula(A ~ 1), Gmin = 0.01, piV = c(1/2, 
    1/3, 1/6), family = c("beta", "gamma"), Qbar = Qbar1, Vbar = Vbar1, 
    n = 1000, tm.control = glm.control(maxit = 500), verbose = FALSE)

Arguments

tm.model	A parametric model {\cal G} of treatment mechanisms. The procedure targets the optimal treatment mechanism within this model. Defaults to formula(A~1).
Gmin	A small positive numeric, the minimum value of elements of the parametric model {\cal G} of treatment mechanisms (see argument tm.model). The maximum value is 1-Gmin.
piV	Marginal distribution of V. Defaults to c(1/2, 1/3, 1/6).
family	A character, either "beta" (default) or "gamma", the nature of the law of outcome.
Qbar	A function, the conditional expectation of Y given (A,W). Defaults to Qbar1.
Vbar	A function, the conditional variance of Y given (A,W). Defaults to Vbar1.
n	An integer, the sample size of the simulated data set used to compute the optimal treatment mechanism.
tm.control	A list of options to pass to glm for the targeting of the treatment mechanism within the model defined by argument 'tm.model'. Defaults to glm.control(maxit=500).
verbose	A logical or an integer indicating the level of verbosity (defaults to 'FALSE').

Value

Returns the optimal treatment mechanism within the parametric model {\cal G}.

Author(s)

Antoine Chambaz [aut, cre]

See Also

getSample, getOptVar

achambaz/tsml.cara.rct documentation built on May 10, 2019, 5:10 a.m.