overlaying two normal distributions over two histograms on one plot in R

Question

I'm trying to graph two normal distributions over two histograms in the same plot in R. Here is an example of what I would like it to look like:

Here is my current code but I'm not getting the second Normal distribution to properly overlay:

g = R_Hist$`AvgFeret,20-60`
m<-mean(g)
std<-sqrt(var(g))

h <- hist(g, breaks = 20, xlab="Average Feret Diameter", main = "Histogram of 60-100um beads", col=adjustcolor("red", alpha.f =0.2))
xfit <- seq(min(g), max(g), length = 680)
yfit <- dnorm(xfit, mean=mean(g), sd=sd(g))
yfit <- yfit*diff(h$mids[1:2]) * length(g)

lines(xfit, yfit, col = "red", lwd=2)

k = R_Hist$`AvgFeret,60-100`
ms <-mean(k)
stds <-sqrt(var(k))

j <- hist(k, breaks=20, add=TRUE, col = adjustcolor("blue", alpha.f = 0.3))
xfit <- seq(min(j), max(j), length = 314)
yfit <- dnorm(xfit, mean=mean(j), sd=sd(j))
yfit <- yfit*diff(j$mids[1:2]) * length(j)

lines(xfit, yfit, col="blue", lwd=2)

and here is the graph this code is generating:

I haven't yet worked on figuring out how to rescale the axis so any help on that would also be appreciated, but I'm sure I can just look that up! Should I be using ggplot2 for this application? If so how do you overlay a normal curve in that library?

Also as a side note, here are the errors generated from graphing the second (blue) line:

score 1 · Accepted Answer · answered Aug 27 '20 at 05:15

To have them on the same scale, the easiest might be to run hist() first to get the values.

h <- hist(g, breaks = 20, plot = FALSE)
j <- hist(k, breaks = 20, plot = FALSE)

ymax <- max(c(h$counts, j$counts))
xmin <- 0.9 * min(c(g, k))
xmax <- 1.1 * max(c(g,k))

Then you can simply use parameters xlim and ylim in your first call to hist():

h <- hist(g, breaks = 20,
          xlab="Average Feret Diameter",
          main = "Histogram of 60-100um beads",
          col=adjustcolor("red", alpha.f =0.2),
          xlim=c(xmin, xmax),
          ylim=c(0, ymax))

The errors for the second (blue) line are because you didn't replace j (the histogram object) with k (the raw values):

xfit <- seq(min(k), max(k), length = 314)
yfit <- dnorm(xfit, mean=mean(k), sd=sd(k))
yfit <- yfit*diff(j$mids[1:2]) * length(k)

As for the ggplot2 approach, you can find a good answer here and in the posts linked therein.

Thank you!!! This was one of those moments where no matter how many times you look at the question you still come up with 22-2=11... — IdRatherNot, Aug 28 '20 at 04:31

overlaying two normal distributions over two histograms on one plot in R

1 Answers1