arm: multicomp.plot – R documentation

Pricing

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

Get Started for Free

Documentation

arm

multicomp.plot

Multiple Comparison Plot

Description

Plots significant difference of simulated array.

Usage

multicomp.plot(object, alpha = 0.05, main = "Multiple Comparison Plot",
  label = NULL, shortlabel = NULL, show.pvalue = FALSE,
  label.as.shortlabel = FALSE, label.on.which.axis = 3,
  col.low = "lightsteelblue", col.same = "white", col.high = "lightslateblue",
  vertical.line = TRUE, horizontal.line = FALSE,
  vertical.line.lty = 1, horizontal.line.lty = 1, mar=c(3.5,3.5,3.5,3.5))

Arguments

`object`	Simulated array of coefficients, columns being different variables and rows being simulated result.
`alpha`	Level of significance to compare.
`main`	Main label.
`label`	Labels for simulated parameters.
`shortlabel`	Short labels to put into the plot.
`show.pvalue`	Default is FALSE, if set to TRUE replaces short label with Bayesian p value.
`label.as.shortlabel`	Default is FALSE, if set to TRUE takes first 2 character of label and use it as short label.
`label.on.which.axis`	default is the 3rd (top) axis.
`col.low`	Color of significantly low coefficients.
`col.same`	Color of not significant difference.
`col.high`	Color of significantly high coefficients.
`vertical.line`	Default is TRUE, if set to FALSE does not draw vertical line.
`horizontal.line`	Default is FALSE, if set to TRUE draws horizontal line.
`vertical.line.lty`	Line type of vertical line.
`horizontal.line.lty`	Line type of horizontal line.
`mar`	A numerical vector of the form `c(bottom, left, top, right)` which gives the number of lines of margin to be specified on the four sides of the plot. The default is `c(3.5,3.5,3.5,3.5)`.

Value

`pvalue`	Array of Bayesian p value.
`significant`	Array of significance.

Author(s)

Masanao Yajima yajima@stat.columbia.edu, Andrew Gelman gelman@stat.columbia.edu

References

Andrew Gelman and Jennifer Hill. (2006). Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press.

Examples

old.par <- par(no.readonly = TRUE)

# example 1
simulation.array <- data.frame(coef1=rnorm(100,10,2), coef2=rnorm(100,5,2),
                      coef3=rnorm(100,0,1), coef4=rnorm(100,-5,3),
                      coef5=rnorm(100,-2,1))
short.lab <- c("c01", "c02", "c03", "c04", "c05")
multicomp.plot(simulation.array[,1:4], label.as.shortlabel=TRUE)

# wraper for multicomp.plot
mcplot(simulation.array, shortlabel = short.lab)

# example 2
data(lalonde)
M1 <- lm(re78 ~ treat + re74 + re75 + age + educ + u74 + u75, data=lalonde)
M1.sim <- sim(M1)
lm.sim <- coef(M1.sim)[,-1]
multicomp.plot(lm.sim, label.as.shortlabel=TRUE, label.on.which.axis=2)

par(old.par)

arm

Data Analysis Using Regression and Multilevel/Hierarchical Models

v1.11-2

GPL (> 2)

Authors

Andrew Gelman [aut], Yu-Sung Su [aut, cre], Masanao Yajima [ctb], Jennifer Hill [ctb], Maria Grazia Pittau [ctb], Jouni Kerman [ctb], Tian Zheng [ctb], Vincent Dorie [ctb]

Initial release

2020-7-27