estimate_g {tmleLite}R Documentation

Estimate Treatment or Missingness Mechanism

Description

An internal function called by the tmle function to obtain an estimate of P(A=1|W), treatment, or P(Delta=1|A,W), missingness. The estimate can be based on user-supplied values, a user-supplied regression formula, or a model selected data-adaptively by the DSA algorithm. If DSA is not available, estimation is based on main terms regression using glm.

Usage

estimate_g(g, DSAargs, A, W, Delta, wts, id)

Arguments

g a vector of values for P(A=1|W) or P(Delta=1|A,W)
DSAargs an optional list specifying values for all arguments to the DSA algorithm
A binary treatment indicator, 1 - treatment, 0 - control
W vector, matrix, or dataframe containing baseline covariates
Delta indicator of missing outcome or treatment assignment. 1 - observed, 0 - missing
wts optional weights on observations. Defaults to unweighted
id id identifying repeated measures

Value

g1W a vector containing values for P(A=1|W) (or P(Delta=1|A,W))
coef coefficients for each term in the working model used for estimation
type type of estimation procedure: NULL-user supplied, ‘glm’-glm, ‘DSA’-model selected by DSA

Author(s)

Susan Gruber

See Also

tmle, estimate_Q, DSA


[Package tmleLite version 1.0-1 Index]