Learn R Programming

SimpleTable (version 0.1-2)

plot.SimpleTable: Summary plots of SimpleTable objects.

Description

plot.SimpleTable summarizes a SimpleTable object by plotting the psterior density of the prima facie and sensitivity analysis causal effects.

Usage

"plot"(x, estimand = c("ATE", "ATT", "ATC", "RR", "RRT", "RRC", "logRR", "logRRT", "logRRC"), percent = 95, plot.bounds = TRUE, plot.pf = TRUE, plot.sens = TRUE, plot.prior = FALSE, color.bounds = "cyan", color1.pf = "lawngreen", color2.pf = "green", color1.sens = "magenta3", color2.sens = "purple4", color.prior = "lightgray", ymax = NULL, ...)

Arguments

x
An object of class SimpleTable produced by analyze2x2 or analyze2x2xK that is to be graphically summarized.
estimand
The causal estimand of interest. Options include: ATE (average treatment effect), ATT (average treatment effect on the treated), ATC (average treatment effect on the controls), RR (relative risk), RRT (relative risk on the treated), RRC (relative risk on the controls), logRR (log relative risk), logRRT (log relative risk on the treated), and logRRC (log relative risk on the controls).
percent
A number between 0 and 100 (exclusive) giving the size of the highest posterior density regions to be calculated and plotted. Default value is $95$.
plot.bounds
Logical value indicating whether the large-sample nonparametric bounds should be plotted. Default value is TRUE.
plot.pf
Logical value indicating whether the posterior density of the prima facie causal effect should be plotted. Default value is TRUE.
plot.sens
Logical value indicating whether the posterior density of the sensitivity analysis causal effect should be plotted. Default value is TRUE.
plot.prior
Logical value indicating whether the prior density of the causal effect of interest should be plotted. Default value is FALSE.
color.bounds
The color of the line segment depicting the large-sample nonparametric bounds. Default value is cyan.
color1.pf
The color of the prima facie posterior density in regions outside the percent% highest posterior density region. Default value is lawngreen.
color2.pf
The color of the prima facie posterior density in regions inside the percent% highest posterior density region. Default value is green.
color1.sens
The color of the sensitivity analysis posterior density in regions outside the percent% highest posterior density region. Default value is magenta3.
color2.sens
The color of the sensitivity analysis posterior density in regions inside the percent% highest posterior density region. Default value is purple4.
color.prior
The color of the prior density of the causal effect of interest. Default value is lightgray.
ymax
The maximum height of the $y$-axis. If NULL (the default) then ymax is taken to be the maximum ordinate of the prima facie posterior density, the sensitivity analysis posterior density, and the prior density.
...
Other arguments to be passed.

Details

See Quinn (2008) for the a description of these plots along with the associated terminology and notation.

References

Quinn, Kevin M. 2008. ``What Can Be Learned from a Simple Table: Bayesian Inference and Sensitivity Analysis for Causal Effects from 2 x 2 and 2 x 2 x K Tables in the Presence of Unmeasured Confounding.'' Working Paper.

See Also

ConfoundingPlot, analyze2x2, analyze2x2xK, ElicitPsi, summary.SimpleTable

Examples

Run this code
## Not run: 
# ## Example from Quinn (2008)
# ## (original data from Oliver and Wolfinger. 1999. 
# ##   ``Jury Aversion and Voter Registration.'' 
# ##     American Political Science Review. 93: 147-152.)
# ##
# ##        Y=0       Y=1
# ## X=0    19        143
# ## X=1    114       473
# ##
# 
# ## a prior belief in an essentially negative monotonic treatment effect 
# S.mono <- analyze2x2(C00=19, C01=143, C10=114, C11=473, 
#                      a00=.25, a01=.25, a10=.25, a11=.25,
# 		     b00=0.02, c00=10, b01=25, c01=3, 
#                      b10=3, c10=25, b11=10, c11=0.02)
# 
# ## ATE (the default)
# plot(S.mono)
# 
# ## ATC instead of ATE
# plot(S.mono, estimand="ATC")
# 
# ## different colors
# plot(S.mono, estimand="ATC", color1.pf="red", color2.pf="blue",
#      color1.sens="gray", color2.sens="orange")
#    
# ## End(Not run)

Run the code above in your browser using DataLab