Estimate Mediation Indirect Effects — med

med_ind estimates the indirect effects of an independent variable on a dependent variable through a mediator using Monte Carlo simulations (Selig & Preacher, 2008). It calculates the distribution of the product of path coefficients (a*b) and provides confidence intervals for the indirect effect, along with a ggplot histogram for visualization.

Usage

med_ind(
  a,
  b,
  var_a,
  var_b,
  cov_ab,
  ci = 95,
  iterations = 20000,
  seed = 1,
  theme = causalverse::ama_theme()
)

Arguments

a: The regression coefficient for the effect of the independent (causal) variable on the mediator.
b: The regression coefficient for the effect of the mediator on the dependent (outcome) variable.
var_a: The variance of the coefficient a.
var_b: The variance of the coefficient b.
cov_ab: The covariance between coefficients a and b.
ci: The confidence interval width for the indirect effect (default is 95 for a 95% CI).
iterations: The number of iterations for the Monte Carlo simulation (default is 20000).
seed: The seed for random number generation to ensure reproducibility (default is 1).
theme: Custom theme that follows ggplots2 (default is AMA style)

Value

A list containing the lower quantile, upper quantile, raw simulation data, and histogram plot of the indirect effects.

References

Selig, J. P., & Preacher, K. J. (2008, June). Monte Carlo method for assessing mediation: An interactive tool for creating confidence intervals for indirect effects [Computer software]. Available from http://quantpsy.org/.

Examples

if (FALSE) { # \dontrun{
result <- med_ind(a = 0.5, b = 0.7, var_a = 0.04, var_b = 0.05, cov_ab = 0.01)
result$lower_quantile
result$upper_quantile
result$plot
} # }