mediateDS: Causal Mediation Analysis
In datashield/dsMediation: DataSHIELD Server side Mediation Analysis Functions

View source: R/mediateDS.R

mediateDS

R Documentation

Causal Mediation Analysis

Description

This function is similar to R function mediate from the mediation package.

Usage

mediateDS(
  model.m,
  model.y,
  treat,
  mediator,
  boot,
  conf.level,
  robustSE,
  sims,
  seed,
  newobj
)

Arguments

`model.m`	a string character, the name of a fitted model object for mediator.
`model.y`	a string character, the name of a fitted model object for outcome.
`treat`	a character string indicating the name of the treatment variable used in the models. The treatment can be either binary (integer or a two-valued factor) or continuous (numeric).
`mediator`	a character string indicating the name of the mediator variable used in the models.
`boot`	a logical value. if 'FALSE' a quasi-Bayesian approximation is used for confidence intervals; if 'TRUE' nonparametric bootstrap will be used. Default is 'FALSE'.
`conf.level`	the level of the returned two-sided confidence intervals.
`robustSE`	a logical value. If 'TRUE', heteroskedasticity-consistent standard errors will be used in quasi-Bayesian simulations. Ignored if 'boot' is 'TRUE' or neither 'model.m' nor 'model.y' has a method for vcovHC in the sandwich package. Default is 'FALSE'.
`sims`	a number of Monte Carlo draws for nonparametric bootstrap or quasi-Bayesian approximation.
`seed`	a number of a seed random number generator. Default value is NULL.
`newobj`	a character string that provides the name for the output object that is stored on the data servers. Default `med.out`.

Details

The function 'mediate' is used to estimate various quantities for causal mediation analysis, including average causal mediation effects (indirect effect), average direct effects, proportions mediated, and total effect.