icedr: Double Robust Sequential Regression Estimation

Description Usage Arguments Value

Description

icedr Estimates the parameter of interest (E[Y_d]) by using the sequential regression approach as presented by Bang and Robins (2005). This function only works in the setting where the outcome is binary or the outcome is continuous with a censoring intervention

Usage

1
2
3
icedr(data, Ynodes, Anodes, Cnodes = NULL, abar, cum.g, Qform,
  SL.library = NULL, family = "quasibinomial", g.weight = FALSE,
  stratify = TRUE)

Arguments

data

data frame following the time-ordering of the nodes.

Ynodes

column names or indicies in data of outcome nodes.

Anodes

column names or indicies in data of treatment nodes.

Cnodes

column names or indicies in data of censoring nodes.

abar

binary vector (numAnodes x 1) of counterfactual treatment

cum.g

a matrix of the cumulative probabilities of treatment (and being uncensored) given the parents.

Qform

character vector of regression formulas for Qbar.

SL.library

optional character vector of libraries to pass to SuperLearner. NULL indicates glm should be called instead of SuperLearner.

family

Currently allows gaussian or binomial to describe the error distribution. Link function information will be ignored.

g.weight

if TRUE, then use the g fits as weights in the Qbar fit, rather than as a covariate.

stratify

if TRUE condition on following abar when estimating Qbar. If FALSE, pool over all subjects.

Value

icedr returns a list of items as an object of class icedr, which include


tranlm/lrecCompare documentation built on May 31, 2019, 7:44 p.m.