Was doing a little presentation to our research group and had to explain the difficulties of ‘collapsing’ longitudinal data into a single measure when the Y var is quite variable. For the particular Y var of interest, it represents burden of disease, so a high Y var for a long time is indicative of high risk, compared to a low value for a similar time. Hence you have issues using with the mean, or the AUC. There’s a lot more to it than that, but that’s the gist of the point of this graph. Sharing the code cause it might be useful to someone else at some point.

I wrote this post in RStudio using the R Markdown language and then knitr to turn in into markdown (.md), and then pandoc to turn it into html. The original file is available here on github.

system(“pandoc -s ggplot_post_text_example.md -o ggplot_post_text_example.html”)

Set up dummy data

library(ggplot2)

# Set up the data and text separately
dat <- data.frame(frame = c(rep("A", 6), rep("B", 2), rep("C", 11), rep("D", 
    11)), y = c(rep(10, 6), rep(10, 2), rep(5, 11), seq(5, 10, 0.5)), x = c(seq(13, 
    18, 1), seq(17, 18, 1), seq(8, 18, 1), seq(8, 18, 1)))

txt <- data.frame(label = c("Mean - 10", "AUC - 50", "Mean - 10", "AUC - 1", 
    "Mean - 5", "AUC - 50", "Mean - 7.5", "AUC - 75"), x = rep(17.5, 8), y = rep(c(13.5, 
    12), 4), frame = c(rep("A", 2), rep("B", 2), rep("C", 2), rep("D", 2)))

And here’s the plot

ggplot(data = dat, aes(x = x, ymax = y, ymin = 0)) + geom_ribbon(data = dat) + 
    facet_wrap(~frame) + scale_y_continuous(limits = c(-0.1, 14)) + scale_x_continuous(limits = c(5, 
    20)) + labs(y = "Y var", x = "X var") + geom_text(data = txt, aes(y = y, 
    label = label))