intsPlot {modnets}

Plot confidence intervals for interaction terms

Description

Allows one to plot the confidence intervals associated with interaction terms. Provides an easy way to look at whether there are any significant interactions, and if so which interactions are important.

Usage

intsPlot(out, y = "all", nsims = 500, alpha = 0.05)

Arguments

out

GGM moderated network output from fitNetwork, or output from a moderated between-subjects network fit with mlGVAR (e.g., when bm = TRUE).

y

Character string. The name of the outcome variable for which to create the plot. If y = "all", then all interaction terms associated with all outcomes will be plotted.

nsims

The number of simulations to estimate the posterior distribution of the difference between high and low levels of the confidence interval.

alpha

Alpha level that is used to compute confidence intervals.

Details

The default setting y = "all" shows all interaction terms associated with the model. But the user can also home-in on specific variables to see what interactions might be relevant. When y = "all", the axis labels should be explained. These follow the format of predictor:outcome. The title reflects the name of the moderator variable. For instance, if a variable named "M" moderates the relationship between "X" and "Y", where "X" predicts "Y", the title of the plot will list the variable "M" as the moderator, and the label (shown on the y-axis), will read "X:Y". When y != "all" (that is, a specific value for y is provided), then the title will still reflect the moderator, but the labels will simply show which predictor interacts with that moderator to predict the outcome.

Value

A plot showing the spread of different interactions.

See Also

fitNetwork, plotNet, mlGVAR

Examples

fit <- fitNetwork(ggmDat, 'M')
plot(fit, 'ints', y = 'all')