modmed.plot {moderate.mediation}

Visual Representation of the Causal Moderated Mediation Analysis Results

Description

'modmed.plot' is used to visualize results from modmed function. This applies only if moderators.disc or moderators.cont is not NULL. The plot consists of two parts. The top represents the sampling distribution of the specified causal effect as a function of the specified moderator within the given levels of the other moderators. The bottom represents the distribution of the specified moderator on the x axis.

Usage

modmed.plot(
  object,
  effect,
  moderator,
  other.mod.disc.values = NULL,
  other.mod.cont.values = NULL,
  is.dist.moderator = FALSE,
  probs = c(0.1, 0.25, 0.5, 0.75, 0.9),
  ncore = 2
)

Arguments

object

Output from the modmed function.

effect

A character string indicating which causal effect to be plotted. effect can be specified as "TE", "TIE", "PIE", "PDE", "TDE", "INT", "TE.ref", "TIE.ref", "PIE.ref", "PDE.ref", "TDE.ref", "INT.ref", "TE.dif", "TIE.dif", "PIE.dif", "PDE.dif", "TDE.dif", or "INT.dif".

moderator

A character string indicating which moderator to be plotted. It must be one of the moderators specified in the function of modmed.

other.mod.disc.values

A vector of values of the other discrete moderators given which the conditional effect at each value of the specified moderator is estimated. The order of other.mod.disc.values should be the same as moderators.disc specified in the function of modmed, with the specified moderator removed if the specified moderator is discrete. If one does not want to condition some moderators on specific values, one may specify their values to be NA. NULL if there are no other discrete moderators.

other.mod.cont.values

A vector of values of the other continuous moderators given which the conditional effect at each value of the specified moderator is estimated. The order of other.mod.cont.values should be the same as moderators.cont specified in the function of modmed, with the specified moderator removedif the specified moderator is continuous. If one does not want to condition some moderators on specific values, one may specify their values to be NA. NULL if there are no other continuous moderators.

is.dist.moderator

A logical value. "TRUE" if distribution of the specified moderator is to be plotted at the bottom, and "FALSE" if not. The default is "FALSE".

probs

A vector of percentiles to be plotted on the distribution of the moderator if the moderator is continuous. NULL if is.dist.moderator = FALSE. The default is c(0.1, 0.25, 0.5, 0.75, 0.9).

ncore

The number of cores for parallel computing. The default is the number of CPU cores on the current host minus 1. One core is saved for users to run other programs on the computer while running the R function.

Value

modmed returns causal moderated mediation analysis results. The plot.modmed function plots the results.

Author(s)

Xu Qin and Lijuan Wang

References

Qin, X., & Wang, L. (2023). Causal moderated mediation analysis: Methods and software

Examples

data(newws)
modmed.results = modmed(data = newws, treatment = "treat", mediator = "emp",
    outcome = "depression", covariates.disc = c("emp_prior", "nevmar",
        "hispanic", "nohsdip"), covariates.cont = c("workpref", "attitude",
        "depress_prior"), moderators.disc = "CHCNT", moderators.cont = "ADCPC",
    m.model = list(intercept = c("ADCPC", "CHCNT"), treatment = c("ADCPC",
        "CHCNT"), emp_prior = NULL, nevmar = NULL, hispanic = NULL,
        nohsdip = NULL, workpref = NULL, attitude = NULL, depress_prior = NULL),
    y.model = list(intercept = c("ADCPC", "CHCNT"), treatment = c("ADCPC",
        "CHCNT"), mediator = c("ADCPC", "CHCNT"), tm = c("ADCPC",
        "CHCNT"), emp_prior = NULL, nevmar = NULL, hispanic = NULL,
        nohsdip = NULL, workpref = NULL, attitude = NULL, depress_prior = NULL),
    comp.mod.disc.values = 3, ref.mod.disc.values = 2, comp.mod.cont.values = 5050,
    ref.mod.cont.values = 5050, m.scale = "binary", y.scale = "continuous",
    seed = 1)
modmed.plot(modmed.results, effect = "TIE", moderator = "ADCPC",
    other.mod.disc.values = 1, is.dist.moderator = TRUE, ncore = 1)