DynTxRegime (version 3.2)

optimalClass: Classification Based Estimation of Optimal Dynamic Treatment Regimes

Description

Uses an Augmented Inverse Propensity Weighted Estimator (AIPWE) or an Inverse Propensity Weighted Estimator (IPWE) of the contrast function to define a weighted classification problem. The method is limited to single decision point binary treatment regimes.

Usage

optimalClass(..., moPropen, moMain, moCont, moClass, 
             data, response, txName, iter = 0L, verbose = TRUE)

Arguments

…

ignored. Included to require named input.

moPropen

An object of class "modelObj." This object specifies the model of the propensity score regression and the R methods to be used to obtain parameter estimates and predictions. The method specified to obtain predictions must return the prediction on the scale of the probability, i.e., returned values must be in the interval (0,1). See moPropen for further information.

moMain

An object of class "modelObj." This object specifies the model of the main effects component of the outcome regression and the R methods to be used to obtain parameter estimates and predictions. The method chosen to obtain predictions must return the prediction on the scale of the response variable.

moCont

An object of class "modelObj." This object specifies the models of the contrasts component of the outcome regression and the R methods to be used to obtain parameter estimates and predictions. The method chosen to obtain predictions must return the prediction on the scale of the response variable.

moClass

An object of class "modelObj." This object defines the classification model (covariates to be used) and the R methods to be used to obtain parameter estimates and predictions. The method chosen to obtain predictions must return the predicted category.

data

An object of class "data.frame." The covariates and treatment histories.

response

An object of class "vector." A vector of the outcome of interest.

txName

An object of class "character." The column header of the stage treatment variable as given in input data. Treatment must be binary and will be recoded as 0/1 if not provided as such.

iter

An object of class "numeric." If >0, the iterative method will be used to obtain parameter estimates in the outcome regression step. See iter for further information.

verbose

An object of class "logical." If FALSE, screen prints will be suppressed.

Value

Returns an object of class "OptimalClass" that inherits directly from class "DynTxRegime."

Methods

classif

signature(object = "OptimalClass"): Retrieve value object from classification step. NA for all objects returned by DynTxRegime statistical methods except for those returned by optimalClass().

coef

signature(object = "OptimalClass"): Retrieve parameter estimates for all regression steps.

DTRstep

signature(object = "OptimalClass"): Retrieve description of method used to create object.

estimator

signature(x = "OptimalClass"): Retrieve the estimated value of the estimated optimal regime for the training data set.

fitObject

signature(object = "OptimalClass"): Retrieve value object returned by regression methods.

optTx

signature(x = "OptimalClass", newdata = "missing"): Retrieve the estimated optimal treatment regime for training data set.

optTx

signature(x = "OptimalClass", newdata = "data.frame"): Estimate the optimal treatment regime for newdata.

outcome

signature(x = "OptimalClass"): Retrieve value object returned by outcome regression methods.

plot

signature(x = "OptimalClass"): Generate plots for regression analyses.

print

signature(object = "OptimalClass"): Print main results of analysis.

propen

signature(x = "OptimalClass"): Retrieve value object returned by propensity score regression methods.

show

signature(object = "OptimalClass"): Show main results of analysis.

summary

signature(object = "OptimalClass"): Retrieve summary information from regression analyses.

Details

The user can opt for the IPWE estimator by specifying moMain and moCont as NULL or not providing them in the named input.

The classification method must accept "weights" as a formal argument.

References

Zhang, B., Tsiatis, A. A., Davidian, M., Zhang, M., and Laber, E. B. (2012). Estimating Optimal Treatment Regimes from a Classification Perspective. Stat, 1, 103--114

Examples

# NOT RUN {
library(rpart)

# Load and process data set
  data(bmiData)

  # define response y to be the negative 12 month
  # change in BMI from baseline
  bmiData$y <- -100*(bmiData[,6] - bmiData[,4])/bmiData[,4]

  # Define the propensity for treatment model and methods.
  moPropen <- buildModelObj(model =  ~ 1, 
                            solver.method = 'glm', 
                            solver.args = list('family'='binomial'),
                            predict.method = 'predict.glm',
                            predict.args = list(type='response'))

  # Define the classification model.
  moClass <- buildModelObj(model = ~parentBMI + month4BMI,
                           solver.method = 'rpart',
                           solver.args = list(method="class"),
                           predict.args = list(type='class'))

# IPWE estimator
  estIPWE <- optimalClass(moPropen = moPropen, moClass = moClass,
                          data = bmiData, response = bmiData$y, txName = "A2",
                          iter = 0L)

  # Create modelObj object for main effect component
  moMain <- buildModelObj(model = ~ gender + parentBMI + month4BMI,
                          solver.method = 'lm')

  # Create modelObj object for contrast component
  moCont <- buildModelObj(model = ~ parentBMI + month4BMI,
                          solver.method = 'lm')

# AIPWE estimator
  estAIPWE <- optimalClass(moPropen = moPropen, moMain = moMain, 
                           moCont = moCont, moClass = moClass,
                           data = bmiData, response = bmiData$y, txName = "A2",
                           iter = 0L)

## Available methods

  # Value object returned by classification method
  classif(estAIPWE)

  # Coefficients of the propensity score and outcome regression
  coef(estAIPWE)

  # Description of method used to obtain object
  DTRstep(estAIPWE)

  # Estimated value of estimated optimal treatment for training data
  estimator(estAIPWE)

  # Value object returned by outcome regression method
  fitObject(estAIPWE)

  # Estimated optimal treatment for training data
  optTx(estAIPWE)

  # Estimated optimal treatment for new data
  optTx(estAIPWE, newdata = bmiData)

  # Value object returned by outcome regression method
  outcome(estAIPWE)

  # Plots if defined by outcome regression method
  dev.new()
  par(mfrow = c(2,4))
  plot(estAIPWE)

  dev.new()
  par(mfrow = c(2,4))
  plot(estAIPWE, suppress = TRUE)

  # Value object returned by propensity score regression method
  propen(estAIPWE)

  # Show main results of method
  show(estAIPWE)

  # Show summary results of method
  summary(estAIPWE)

# }