How to customize Bland-Altman plot in R - r

Question

I am trying to compare two measurement methods with Bland-Altman plot, which is basically this:
method.1 <- rnorm(20)
method.2 <- rnorm(20)
plot((method.1 + method.2)/2, method.1 - method.2)
I've found a package that I like:
devtools::install_github("deepankardatta/blandr")
library(blandr)
blandr.draw(method.1, method.2, plotter = "rplot")
Which gives me the following result:
Bland-Altman plot with blandr package
The upper band is Mean + 1.96 SD (+/- 95% CI)
The lower band is Mean - 1.96 SD (+/- 95% CI)
The middle band is Mean +/- 95% CI
I like the way it is, although I wish I could change the bands colours, line types, points shape or include the legend.
I wish I could overwrite the blandr.draw() function or just create my own plot ( same as blandr.draw() ) using base R so I can customize it the way I want. I failed to contact the package author...
Additionally - ggplot version of similar plot ( blandr.draw(method.1, method.2) ) will be appreciated.

Answer 1

So here is my self-made Bland-Altman plot - maybe it will be useful for others.
Sample Bland-Altman plot
All calculations (Lines of agreement and 95% Confidence Intervals) based on Bland and Altman paper from 1999: Measuring agreement in method comparision studies.
I still don't know how to shade bands between Confidence Intervals - probably with rect() function.
# Sample data:
method.1 <- rnorm(100)
method.2 <- rnorm(100)
df <- data.frame(
X = (method.1 + method.2)/2,
Y = (method.1 - method.2)
)
# Number of measurements to calculate degrees of freedom for t-distribution:
n = length(df$Y)
t = qt(0.975, df = n - 1) # t-distribution
mean <- mean(df$Y)
LoA <- 1.96*sd(df$Y) # Lines of Agreement
# 95% Confidence Intervals:
LoA_CI <- t * sqrt( (1/n + 3.8416/(2*(n - 1))) ) * sd(df$Y)
mean_CI <- t * sd(df$Y)/sqrt(n)
# To calculate position of partition lines:
LoA_up_plus <- mean + LoA + LoA_CI
LoA_up <- mean + LoA
LoA_up_minus <- mean + LoA - LoA_CI
mean_plus <- mean + mean_CI
mean_minus <- mean - mean_CI
LoA_down_plus <- mean - LoA + LoA_CI
LoA_down <- mean - LoA
LoA_down_minus <- mean - LoA - LoA_CI
# Save PNG file:
png(filename = "BA_norm.png",
width = 3000, height = 2100, units = "px", res = 300)
# Plot:
plot(Y ~ X, df,
# When I have a lot of data my points are overlapping each other
# that's why I make them semi-transparent with 'alpha':
col = rgb(0, 0, 0, alpha = 0.5), pch = 16, cex = 0.75,
main = "Bland-Altman plot for Mathod 1 and Method 2",
xlab = "Mean of results",
ylab = "Method 1 - Method 2 difference"
)
# Background colour for your plot, if you don't want it
# just skip following four lines of code:
rect(par("usr")[1], par("usr")[3], par("usr")[2], par("usr")[4],
col = "#c2f0f0") #here you can put desired background colour hex
points(Y ~ X, df,
col = rgb(0, 0, 0, alpha = 0.5), pch = 16, cex = 0.75)
# Adding lines:
abline(h = 0, lwd = 0.7) # solid line for Y = 0
# Display rounded values of partition lines positions:
text(x = 1.5, y = LoA_up_plus, # x and y position of text
paste(round(LoA_up, 2), "\u00B1", round(LoA_CI, 2)), pos = 1)
abline(h = LoA_up_plus, col = "#68cbf8", lty = "dotted")
abline(h = LoA_up, col = "blue", lty = "dashed")
abline(h = LoA_up_minus, col = "#68cbf8", lty = "dotted")
text(x = 1.5, y = mean_plus,
paste(round(mean, 2), "\u00B1", round(mean_CI, 2)), pos = 3)
abline(h = mean_plus, col = "#ff9e99", lty = "dotted")
abline(h = mean, col = "red", lty = "longdash")
abline(h = mean_minus, col = "#ff9e99", lty = "dotted")
text(x = 1.5, y = LoA_down_plus,
paste(round(LoA_down, 2), "\u00B1", round(LoA_CI, 2)), pos = 3)
abline(h = LoA_down_plus, col = "#68cbf8", lty = "dotted")
abline(h = LoA_down, col = "blue", lty = "dashed")
abline(h = LoA_down_minus, col = "#68cbf8", lty = "dotted")
# Close saving PNG file function:
dev.off()
I guess it is possible to easily condense all those abline() functions.