SubgrPlots (version 0.1.0)

plot_labbe: L'Abbe plot for subgroup effect size

Description

this function produces a L'Abbe plot showing the treatment effect size of subgroups defined by the categories of covariates. The x-axis and y-axis represent the treatment effect estimate from the control and treatment group, respectively. The dashed dignal indicates no effect, and the solid diagnal line corresponds to the full population effect estimate. The squares represent subgroups, and the red or blue dashed lines have a length which show the magnitude of the lower or upper bound of the 95 treatment effect estimates. If the solid diagonal line cross all the blue or red lines, it may indicate homogeneity across subgroup with repective to the full population effect estimate. Note that the overall size of squares which represent subgroups can be adjusted by setting different values on the associated input argument. In addition, the function uses log odd ratio for displaying subgroup effect sizes in binary and survival data, respectively.

Usage

plot_labbe(dat, covari.sel, trt.sel, resp.sel, outcome.type, effect = c("HR",
  "RMST"), size.shape = 1/18, adj.ann.subgrp = 1/30, font.size = c(1, 1,
  0.85, 0.85), title = NULL, lab.xy = NULL, time = mean(dat[,
  resp.sel[1]]), show.ci = 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".

effect

Either "HR" of "RMST". Only when outcome.type = "survival"

size.shape

a parameter controlling the height and width of the squares and the size is proportional to the ratio of subgroup sample sizes over the full population size.

adj.ann.subgrp

a parameter controlling the distance between a square and its corresponding subgroup label; also, the line gap between the legend text for subgroups.

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 the corresponding squares.

title

a string specifying the main title.

lab.xy

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

time

time for calculating the survival in each subgroup

show.ci

A logical indicating whether to show an additional line for confidence intervals

Examples

# NOT RUN {
library(dplyr)

# Load the data to be used
data(prca)
dat <- prca
dat %>%
  mutate(bm = factor(ifelse(bm == 0 , "No", "Yes")),
         hx = factor(ifelse(hx == 0 , "No", "Yes")))-> dat

## 8. Labbe Plot -----------------------------------------------------------
lab.xy = list("Control Group Estimate", "Treatment Group Estimate")
plot_labbe(dat = dat,
           covari.sel = c(4,5,6,7),
           trt.sel = 3,
           resp.sel = c(1,2),
           outcome.type = "survival",
           effect = "RMST",
           lab.xy = lab.xy,
           size.shape = 0.2,
           adj.ann.subgrp = 1/30,
           time=50, show.ci = FALSE)

# }