SubgrPlots (version 0.1.0)

plot_mosaic: Mosaic plot

Description

This function produces a mosaic plot for subgroup analysis

Usage

plot_mosaic(dat, covari.sel, trt.sel, resp.sel, outcome.type, range.v = NULL,
  adj.ann.subgrp = 4, range.strip = c(-3, 3), n.brk = 30,
  n.brk.axis = NULL, font.size = c(1, 1, 0.85, 0.85, 1), title = NULL,
  lab.xy = NULL, strip = "default", effect = "HR", lwd. = 2,
  sep. = 0.05, show.overall = TRUE, palette = "divergent",
  col.power = 0.5, print.ss = FALSE, col.line = "white", time = NULL,
  show.marginal = TRUE, show.effect = TRUE)

Arguments

dat

a data set

covari.sel

a vector of indices of the two covariates

trt.sel

a covariate index specifying the treatment code

resp.sel

a covariate index specifying the response variable

outcome.type

a string specifying the type of the response variable, it can be "continuous", or "binary" or "survival".

range.v

a vector specifying the vertical range of graphical display.

adj.ann.subgrp

a parameter adjusting the distance between a point and its corresponding subgroup label. The smaller the value is, the larger the distance is.

range.strip

range for the treatment effect scale

n.brk

number of breaks in the treatment effect scale

n.brk.axis

number of breaks in the axis of the treatment effect scale

font.size

a vector specifying the size of labels and text; the first element is for the main title, the second is for for x-axis and y-axis labels; the thrid is for the legend text of subgroups; the fourth is for the subgroup labels near points; the fifth is for the unit labels on all the axes.

title

a string specifying the main title.

lab.xy

a list of two strings specifying the labels of the x and y axes.

strip

title for the treatment effect scale

effect

either "HR" or "RMST". only when outcome.type = "survival"

lwd.

line width for the mosaics

sep.

separation for the mosaics

show.overall

logical. whether to show or not the overall treatment effect in the strip

palette

either "divergent" or "hcl"

col.power

to be used when palette = "hcl". see colorspace package for reference

print.ss

logival indicating whether to show the sample sizes of subgroups

col.line

color of the mosaics' border

time

time for calculating the RMST

show.marginal

logical indicating whether to show the marginal subgroups. only when 2 covariates are used

show.effect

logical indicating whether to show effect size using color or not. only when 3 covariates are used

Examples

# NOT RUN {
library(dplyr)
data(prca)
dat <- prca
dat %>%
  mutate(bm = factor(ifelse(bm == 0 , "No", "Yes")),
         hx = factor(ifelse(hx == 0 , "No", "Yes")),
         Treatment = factor(ifelse(rx == 0 , "Control", "Treatment")),
         Survival = factor(ifelse(survtime > 24 , "Yes", "No"),
         levels = c("Yes", "No")))-> dat
levels(dat$age_group) = c("Young","Middle-aged","Old")
levels(dat$weight_group)  = c("Low","Mid","High")
# Change variable names
dat %>%
  rename(`Bone Metastasis` = bm,
         `Performance rating` = pf,
         `History of cardiovascular events` = hx,
         `2-year survival` = Survival,
         Weight = weight_group,
         Age = age_group) -> dat
## 2.a Mosaic plot with 2 variables -----------------------------------------
plot_mosaic(dat = dat,
            covari.sel = c(14, 15),
            trt.sel = 3,
            resp.sel = c(1, 2),
            outcome.type =  "survival",
            range.v = NULL,
            adj.ann.subgrp = 4,
            range.strip=c(-3, 3),
            n.brk = 31,
            n.brk.axis = 7, sep. = 0.034,
            font.size = c(10, 10, 10, 10, 0.7),
            title = NULL, lab.xy = NULL,
            strip = "Treatment effect size (log-hazard ratio)",
            col.line = "white", lwd. = 2,
            effect = "HR", print.ss = FALSE, palette = "hcl")

## 2.b Mosaic plot with 3 variables -----------------------------------------
plot_mosaic(dat = dat,
            covari.sel = c(15, 7, 4),
            trt.sel = 3,
            resp.sel = c(1, 2),
            outcome.type =  "survival",
            range.v = NULL, adj.ann.subgrp = 4,
            range.strip=c(-3, 3),
            n.brk = 31, n.brk.axis = 7,
            font.size = c(10, 10, 10, 10, 0.7),
            title = NULL, lab.xy = NULL,
            strip = "Treatment effect size (log-hazard ratio)",
            effect = "HR", palette = "hcl")
# }

Run the code above in your browser using DataCamp Workspace