.make_long_data {nlpred}

Worker function to make long form data set needed for CVTMLE targeting step

Description

Worker function to make long form data set needed for CVTMLE targeting step

Usage

.make_long_data(
  x,
  gn,
  update = FALSE,
  epsilon_0 = 0,
  epsilon_1 = 0,
  tol = 0.001
)

Arguments

x

An entry in the "predictions list" that has certain named values (see ?.get_predictions)

gn

An estimate of the probability that Y = 1.

update

A boolean of whether this is called for initial construction of the long data set or as part of the targeting loop. If the former, empirical "density" estimates are used. If the latter these are derived from the targeted cdf.

epsilon_0

If update = TRUE, a vector of TMLE fluctuation parameter estimates used to add the CDF and PDF of Psi(X) to the data set.

epsilon_1

Same as for epsilon_0.

tol

A truncation level when taking logit transformations.

Value

A long form data list of a particular set up. Columns are named id (multiple rows per observation in validation sample), u (if Yi = 0, these are the values of psi(x) in the training sample for obs with Y = 1, if Yi = 1, these are values of psi(x) in the training sample for obs. with Y = 0), Yi (this observation's value of Y), Fn (estimated value of the cdf of psi(X) given Y = Yi in the training sample), dFn (estimated value of the density of psi(X) given Y = (1-Yi) in the training sample), psi (the value of this observations Psihat(P_n,B_n^0)), gn (estimate of marginal of Y e.g., computed in whole sample), outcome (indicator that psix <= u), logit_Fn (the cdf estimate on the logit scale, needed for offset in targeting model).