stackplot: plot grouped CSMF from a "insilico" object

Description

Produce bar plot of the CSMFs for a fitted "insilico" object in broader groups.

Usage

stackplot(
  x,
  grouping = NULL,
  type = c("stack", "dodge")[1],
  order.group = NULL,
  order.sub = NULL,
  err = TRUE,
  CI = 0.95,
  sample.size.print = FALSE,
  xlab = "Group",
  ylab = "CSMF",
  ylim = NULL,
  title = "CSMF by broader cause categories",
  horiz = FALSE,
  angle = 60,
  err_width = 0.4,
  err_size = 0.6,
  point_size = 2,
  border = "black",
  bw = FALSE,
  ...
)

Arguments

x: fitted "insilico" object
grouping: C by 2 matrix of grouping rule. If set to NULL, make it default.
type: type of the plot to make
order.group: list of grouped categories. If set to NULL, make it default.
order.sub: Specification of the order of sub-populations to plot
err: indicator of inclusion of error bars
CI: confidence interval for error bars.
sample.size.print: Logical indicator for printing also the sample size for each sub-population labels.
xlab: Labels for the causes.
ylab: Labels for the CSMF values.
ylim: Range of y-axis.
title: Title of the plot.
horiz: Logical indicator indicating if the bars are plotted horizontally.
angle: Angle of rotation for the texts on x axis when horiz is set to FALSE
err_width: Size of the error bars.
err_size: Thickness of the error bar lines.
point_size: Size of the points.
border: The color for the border of the bars.
bw: Logical indicator for setting the theme of the plots to be black and white.
...: Not used.

Author

Zehang Li, Tyler McCormick, Sam Clark

Maintainer: Zehang Li <lizehang@uw.edu>

References

Tyler H. McCormick, Zehang R. Li, Clara Calvert, Amelia C. Crampin, Kathleen Kahn and Samuel J. Clark Probabilistic cause-of-death assignment using verbal autopsies, Journal of the American Statistical Association (2016), 111(515):1036-1049.

Examples

Run this code

if (FALSE) {
  data(RandomVA1) 
  ##
  ## Scenario 1: without sub-population specification
  ##
  fit1<- insilico(RandomVA1, subpop = NULL,  
                Nsim = 1000, burnin = 500, thin = 10 , seed = 1,
                auto.length = FALSE)
  # stack bar plot for grouped causes
  # the default grouping could be seen from
  data(SampleCategory)
  stackplot(fit1, type = "dodge", xlab = "")
  
  ##
  ## Scenario 2: with sub-population specification
  ##
  data(RandomVA2)
  fit2<- insilico(RandomVA2, subpop = list("sex"),  
                Nsim = 1000, burnin = 500, thin = 10 , seed = 1,
                auto.length = FALSE)
  stackplot(fit2, type = "stack", angle = 0)
  stackplot(fit2, type = "dodge", angle = 0)
  # Change the default grouping by separating TB from HIV
  data(SampleCategory)
  SampleCategory[c(3, 9), ]
  SampleCategory[3, 2] <- "HIV/AIDS"
  SampleCategory[9, 2] <- "TB"
  stackplot(fit2, type = "stack", grouping = SampleCategory, 
            sample.size.print = TRUE, angle = 0)
  stackplot(fit2, type = "dodge", grouping = SampleCategory,
            sample.size.print = TRUE, angle = 0)
  
  # change the order of display for sub-population and cause groups
  groups <- c("HIV/AIDS", "TB", "Communicable", "NCD", "External",
              "Maternal", "causes specific to infancy") 
  subpops <- c("Women", "Men")
  stackplot(fit2, type = "stack", grouping = SampleCategory, 
            order.group = groups, order.sub = subpops, 
            sample.size.print = TRUE, angle = 0)	
}