plot.medsens: Plotting results from sensitivity analysis of mediation effects.

Description

Plots results from medsens function. Y axis plots mediation effect and x-axis plots the error correlation rho. Standard options for plot function available.

Usage

## S3 method for class 'medsens':
plot(x, sens.par="rho", r.type=1, sign.prod=1, pr.plot=FALSE, smooth.effect=FALSE, smooth.ci=FALSE, levels=NULL, xlab=NULL, ylab=NULL, xlim=NULL, ylim=NULL, main=NULL, ...)
 # ## S3 method for class 'plot.medsens':
print(z)

Arguments

output from medsens function.

sens.par

type of sensitivity interpretation to be plotted. Default plots mediation effects in terms of sensitivity parameter rho. If "R2" is specified then in terms of variances explained by an unobserved pretreatment confounder.

r.type

type of R square interpretation to be used. If 1 is specified then proportion of previously unexplained variance is used. If 2 is specified then proportion of total unexplained variance is used. Only relevant if sens.par is set to "R2".

sign.prod

whether the omitted variable affects the mediator and outcome variable in the same direction (1) or different directions (-1). Only relevant if sens.par is set to "R2".

pr.plot

if pr.plot=TRUE then proportion mediated will be plotted.

smooth.effect

whether the estimated mediation effects are smoothed via a lowess smoother before being plotted.

smooth.ci

whether the confidence bands are smoothed via a lowess smoother before being plotted.

levels

vector of levels at which to draw contour lines. Only relevant if sens.par is set to "R2".

xlab

x-axis label.

ylab

y-axis label.

xlim

range for x-axis.

ylim

range for y-axis.

main

main title for graph.

...

additional arguments to be passed.

Warning

The smooth.effect and smooth.ci options should be used with caution since the smoothing could affect substantive implications of the graphical analysis in a significant way.

References

Imai, Kosuke, Luke Keele and Dustin Tingley (2009) A General Approach to Causal Mediation Analysis. Imai, Kosuke, Luke Keele and Teppei Yamamoto (2009) Identification, Inference, and Sensitivity Analysis for Causal Mediation Effects.

Examples

Run this code

#Example with JOBS II Field experiment

data(jobs)

#########################################
#Continuous mediator and continuous outcome
#########################################

#Fit parametric models
model.m <- lm(job_seek ~ treat + depress1, data=jobs)
model.y <- lm(depress2 ~ treat + job_seek + depress1, data=jobs)

#Pass model objects through mediate function
med.cont <- mediate(model.m, model.y, treat="treat", mediator="job_seek", sims=1000)

#Pass mediate output through medsens function
sens.cont <- medsens(med.cont, sims=1000, rho.by=.1)

#Use summary function to display values of rho where 95summary(sens.cont)

#Plot mediation effect and 95plot(sens.cont, main="JOBS", ylim=c(-.2,.2))

#Plot sensitivity analysis using R^2 method. See plot.medsens for additional detail
plot(sens.cont, sens.par="R2", r.type=2, sign.prod=1)