intervention_effect: Calculate Estimates of Causal Effects

In christian-gische/causalSEM: Analyze Causal Effects Using Interventional Distributions

Calculate Estimates of Causal Effects

Description

Calculate estimates of causal effects based on the interventional distribution.

Usage

intervention_effect(
  model = NULL,
  intervention = NULL,
  intervention_level = NULL,
  outcome = NULL,
  effect_type = NULL,
  lower_bound = NULL,
  upper_bound = NULL,
  verbose = NULL,
  ...
)

Arguments

model	Fitted model. The fitted model can be of class lavaan.
intervention	Character vector of names of interventional variables.
intervention_level	Numeric vector of interventional levels. Same length and order as argument intervention. Default: vector of ones.
outcome	Character vector of variable names of outcome variables. Default: all non-interventional variables.
effect_type	Character string describing the features of the interventional distribution to be analyzed. Admissible values are mean (default), variance, density, and probability.
lower_bound	Numeric vector of same length and order as argument outcome. Lower bounds of critical range of outcome variables.
upper_bound	Numeric vector of same length and order as argument outcome. Upper bounds of critical range of outcome variables.
verbose	Integer number describing the verbosity of console output. Admissible values: 0: no output (default), 1: user messages, 2: debugging-relevant messages.

Value

An object of class causalSEM for which several methods are available including summary.causalSEM and print.causalSEM.

References

Gische, C., Voelkle, M.C. (2022) Beyond the Mean: A Flexible Framework for Studying Causal Effects Using Linear Models. Psychometrika 87, 868–901. https://doi.org/10.1007/s11336-021-09811-z

christian-gische/causalSEM documentation built on April 26, 2023, 10:36 p.m.