networkGibbsOuts2Cpp: Estimate components for direct and spillover effects

In isabelfulcher/autognet: Estimation of causal network effects

Description

Given the specific inputs, determine estimates of psi for the given units under some treatment regime and individual treatment value using a Gibbs sampling procedure.

Usage

networkGibbsOuts2Cpp(
  cov_list,
  beta,
  p,
  ncov,
  R,
  N,
  adjacency,
  weights,
  subset,
  treatment_value,
  burnin,
  average
)

Arguments

cov_list	The output from networkGibbsOutCovCpp function
beta	A numeric vector for the parameters from the outcome model
p	A probability of treated units for the binomial treatment assignment draw
ncov	A numeric vector for the parameters from the outcome model
R	An integer indicating the number of iterations for the Gibbs
N	An integer indicating the size of the interconnected network
adjacency	A binary matrix indicating connected units
weights	A numeric vector indicating the number of neighbors for each node
subset	The indices of the individuals, as they appear in the adjacency matrix, to be included in the network causal effects estimates.
treatment_value	The intervened value of an individual's treatment assignment for each person in subset
burnin	The index to start evaluation as one would normally have for a burnin for a Bayesian computation.
average	An indicator of whether to evaluate the causal effects as an average of the R iterations

Value

A vector of length N containing the estimated value of psi for each person

isabelfulcher/autognet documentation built on Aug. 23, 2020, 9:42 a.m.