mcEvalPsi


This R6 class performs the Monte-Carlo evaluation of the target parameters using the data generated under
 the user-specified arbitrary intervention <code>gstar</code>.
 For a given dataset, take <code>E[Y|sA,sW] = m.Q.init</code> and calcualte estimate of <code>psi_n</code> under <code>g_star</code>
 using Monte-Carlo integration:
 (*) <code>W</code> can be iid or not (<code>W</code>'s are never resampled).
 (*) Use <code>P_n(W) = 1</code> for the distribution of <code>W = (W_1,...,W_n)</code> and draw <code>n</code> new exposures
 <code>A=(A_1,...,A_n)</code> from the distribution of <code>g_star</code>.
 (*) Evaluate <code>n</code> summary measures <code>sA=(sA_1,...,sA_n)</code> using these <code>n</code> newly sampled exposures <code>A</code>.
 (*) Evaluate the subsititution estimators as an average of n predictions <code>E[Y=1|sA,sW]</code>.
 (*) Repeat <code>nrep</code> times until convergence of <code>psi_n</code>.


class

Estimation of average causal effects for single time point
interventions in network-dependent data (e.g., in the presence of spillover
and/or interference). Supports arbitrary interventions (static or
stochastic). Implemented estimation algorithms are the targeted maximum
likelihood estimation (TMLE), the inverse-probability-of-treatment (IPTW)
estimator and the parametric G-computation formula estimator. Asymptotically
correct influence-curve-based confidence intervals are constructed for the
TMLE and IPTW. The data are assumed to consist of rows of unit-specific
observations, each row i represented by variables (F.i,W.i,A.i,Y.i), where
F.i is a vector of friend IDs of unit i (i's network), W.i is a vector of
i's baseline covariates, A.i is i's exposure (can be binary, categorical or
continuous) and Y.i is i's binary outcome. Exposure A.i depends on
(multivariate) user-specified baseline summary measure(s) sW.i, where sW.i
is any function of i's baseline covariates W.i and the baseline covariates
of i's friends in F.i. Outcome Y.i depends on sW.i and (multivariate)
user-specified summary measure(s) sA.i, where sA.i is any function of i's
baseline covariates and exposure (W.i,A.i) and the baseline covariates and
exposures of i's friends. The summary measures are defined with functions
def.sW and def.sA. See ?'tmlenet-package' for a general overview.

Oleg Sofrygin

tmlenet

Targeted Maximum Likelihood Estimation for Network Data

mcEvalPsi function

An <code><a rd-options="" href="/link/R6Class?package=tmlenet&version=0.1.0" data-mini-rdoc="tmlenet::R6Class">R6Class</a></code> generator object

Format

 <dl>
  <dt><code>new(DatNet.ObsP0, DatNet.gstar, ...)</code></dt><dd>...</dd> <dt><code>get.gcomp(m.Q.init)</code></dt><dd>...</dd> <dt><code>get.tmleA(m.Q.starA, m.h.fit)</code></dt><dd>...</dd> <dt><code>get.tmleB(m.Q.starB)</code></dt><dd>...</dd> <dt><code>get.fiW()</code></dt><dd>...</dd> </dl> 

Methods

R6 class for Monte-Carlo evaluation of various substitution estimators for exposures generated under the user-specified stochastic intervention function.

mcEvalPsi: R6 class for Monte-Carlo evaluation of various substitution estimators for exposures generated under the user-specified stochastic intervention function.

Description

Usage

Arguments

Format

Methods

Details